CtrlK
BlogDocsLog inGet started
Tessl Logo

cicd-secrets-exfil

Extracting CI secrets / OIDC tokens once you have code execution in a build job — echo/printenv exfil, log-masking bypass (base64, char-split, reversal), OIDC token abuse to assume cloud roles, GITHUB_TOKEN / CI_JOB_TOKEN scope abuse, cache / artifact secret leakage, provenance pivot.

67

Quality

81%

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

SKILL.md
Quality
Evals
Security

Quality

Content

80%

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

An exceptionally actionable, lean reference card of executable CI/CD secret-exfil techniques with a strong safety decision gate. Its weaknesses are structural: a topical rather than sequenced workflow and a monolithic layout with no progressive disclosure.

Suggestions

Add a short numbered workflow at the top (enumerate surface → prove access via len/first4/last4 → demonstrate capability by minting+decoding OIDC → document, don't burn) to give the catalog an explicit sequence with checkpoints.

Move the detection-signatures and tools tables, plus the deeper OIDC/provenance detail, into references/ files (e.g., DETECTION.md, TOOLS.md) referenced one level deep from the body to improve progressive disclosure.

DimensionReasoningScore

Conciseness

Dense, command-driven body that assumes Claude's competence — no padding about what CI/CD or masking is, with every prose note (substring-based masking, deterministic OIDC sub claim) earning its place.

3 / 3

Actionability

Provides fully executable, copy-paste-ready bash throughout — surface-map enumeration, eight masking-bypass variants, the OIDC mint/assume-role exchange, and token-abuse commands — with concrete tool names in tables.

3 / 3

Workflow Clarity

Organized as a technique catalog rather than a strictly sequenced pipeline; the trailing Decision Gate provides explicit checkpoints (print proof not secret, dry-run artifacts, scrub before done), but the main flow lacks a clear validate→fix→retry sequence.

2 / 3

Progressive Disclosure

A single monolithic file with well-labeled sections but no bundle files or one-level-deep references; content that could be split (detection signatures, tool reference, OIDC detail) is all inline.

2 / 3

Total

10

/

12

Passed

Description

82%

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

A highly specific, action-dense description with strong trigger terms and a clear niche, weakened only by the absence of an explicit 'when to use' clause. Voice is appropriately third person.

Suggestions

Add an explicit 'Use when ...' clause naming trigger situations (e.g., 'Use when you have code execution in a CI build job and need to enumerate or prove access to secrets/OIDC tokens') to raise completeness to 3.

Surface a few of the metadata when_to_use keywords into the description so the trigger guidance lives where the model actually reads it.

DimensionReasoningScore

Specificity

Lists many concrete actions — 'echo/printenv exfil, log-masking bypass (base64, char-split, reversal), OIDC token abuse to assume cloud roles, GITHUB_TOKEN / CI_JOB_TOKEN scope abuse, cache / artifact secret leakage, provenance pivot' — matching the multiple-specific-actions anchor.

3 / 3

Completeness

Clearly states what the skill does but lacks any 'Use when...' clause or explicit trigger guidance, so per the judging guidelines completeness is capped at 2.

2 / 3

Trigger Term Quality

Uses the natural terms practitioners say for this niche — 'ci secrets', 'oidc tokens', 'GITHUB_TOKEN', 'CI_JOB_TOKEN', 'base64' — giving good coverage of relevant keywords rather than generic jargon.

3 / 3

Distinctiveness Conflict Risk

A sharply defined niche (CI/CD secrets + OIDC exfiltration from a build job) with distinct, specific triggers that are unlikely to overlap with unrelated skills.

3 / 3

Total

11

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
PurpleAILAB/Decepticon
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.