CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

c2-cobalt-strike

Cobalt Strike operations — Beacon deployment, Malleable C2 profile creation, listener setup, OPSEC-safe beacon configuration, process injection, and Arsenal kit usage.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./packages/decepticon/decepticon/skills/standard/post-exploit/c2-cobalt-strike/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a dense, operator-grade reference with strong actionability — real commands, config blocks, and decision tables rather than prose — and reasonable validation checkpoints (c2lint, ss, error table). Its weakness is structure: everything lives in one monolithic SKILL.md with no reference files, so a large profile example and lookup tables load into context even when not needed.

Suggestions

Split the full Malleable C2 profile example into a references/ file (e.g. references/malleable-profile.md) and link to it from section 4, keeping only the OPSEC-critical settings inline.

Move the Detection Signatures and Tools & Resources lookup tables into a references/ file and link them, leaving the Quick Reference and Decision Gate as the always-loaded overview.

Consider a references/ops-tables.md for the sleep/jitter and process-selection tables to shrink the SKILL.md footprint while keeping one-level-deep navigation.

DimensionReasoningScore

Conciseness

The body is a lean command/config reference that assumes operator knowledge — almost every section is executable material rather than background explanation. Only the two-sentence intro ("Cobalt Strike is a commercial adversary simulation platform...") and mild overlap between the OPSEC Considerations and Detection Signatures tables could be trimmed, fitting 'efficient; minor instances of over-explanation'.

4 / 5

Actionability

Concrete, mostly copy-paste-ready commands and config throughout ("./teamserver <TEAMSERVER_IP> <SHARED_PASSWORD> ...", "./c2lint /workspace/profiles/amazon.profile", "./build.sh pipe VirtualAlloc 310272 5 false false ...", exact sleep/jitter values). Some blocks are GUI-menu walkthroughs in comments rather than executable commands ("Attacks > Packages > Windows Executable (S)"), keeping it below the fully-executable 5 anchor.

4 / 5

Workflow Clarity

Sections follow a logical setup sequence (teamserver → listeners → payload generation → profile → sleep → injection → arsenal) with explicit checkpoints: profile validation via c2lint ("If c2lint fails, the teamserver will refuse to load the profile"), teamserver verification via `ss -tlnp`, a Decision Gate tree, and an Error Handling table mapping symptoms to resolutions. Not 5 because the flow is presented as a reference rather than an ordered procedure with validate-then-proceed gating.

4 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), and ~430 lines are inlined in SKILL.md — including a full ~75-line Malleable C2 profile example, detection-signature tables, and a tools list that clearly belong in separate reference files. Section headers are clear, so it sits at 'some structure but could be better organized; content that should be separate is inline' rather than the 2 anchor's 'minimal structure'.

3 / 5

Total

15

/

20

Passed

Description

71%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong on specificity, enumerating six concrete capabilities in third-person voice, and its trigger terms are domain-accurate. Its main weakness is the missing 'Use when...' clause, which caps completeness and leaves invocation guidance implicit. Adding an explicit trigger clause with common synonyms (teamserver, aggressor, listener) would raise it to the top band.

Suggestions

Append a trigger clause such as "Use when the user mentions Cobalt Strike, teamserver, a beacon, malleable C2 profiles, or the Arsenal kit" to explicitly answer the 'when' question (completeness is currently capped at 3 by the missing 'Use when...' clause).

Fold in common natural synonyms — "teamserver", "aggressor", "C2 listener" — to broaden trigger term coverage beyond the current set.

Keep the third-person action list as-is; it already provides comprehensive, concrete coverage of the tool's capabilities.

DimensionReasoningScore

Specificity

The description lists six concrete, specific actions ("Beacon deployment", "Malleable C2 profile creation", "listener setup", "OPSEC-safe beacon configuration", "process injection", "Arsenal kit usage") covering the tool's full workflow, matching the 'multiple specific concrete actions; comprehensive coverage' anchor. It exceeds the 4 anchor, which allows minor coverage gaps.

5 / 5

Completeness

The 'what' is clearly answered by the enumerated action list, but there is no 'Use when...' clause or equivalent explicit trigger guidance — per judging guidelines this caps completeness at 3 ('when' is missing or only weakly implied by the domain name). Not 4 because nothing in the description states when to invoke it.

3 / 5

Trigger Term Quality

Good natural keyword coverage ("Cobalt Strike", "Beacon", "Malleable C2", "Arsenal kit") that users would plausibly say, but common variations like "teamserver", "aggressor", or "C2 listener" are absent. This fits 'good keyword coverage; a few natural terms missing' rather than the comprehensive synonym coverage of the 5 anchor.

4 / 5

Distinctiveness Conflict Risk

"Cobalt Strike" is a clearly named niche tool, making the description mostly distinct, but closely related C2 skills (e.g., a domain-fronting or generic C2 skill) could plausibly overlap for terms like "beacon" or "C2". Matches 'mostly distinct; minor overlap risk with closely related skills' rather than the minimal-conflict 5 anchor.

4 / 5

Total

16

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

PurpleAILAB/Decepticon

Path

packages/decepticon/decepticon/skills/standard/post-exploit/c2-cobalt-strike/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.