exploit-reporting
Exploitation finding documentation — initial access reports, exploit chain documentation, CVSS v4.0 scoring, shell/credential inventory, detection gap analysis.
56
65%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Fix and improve this skill with Tessl
tessl review fix ./packages/decepticon/decepticon/skills/standard/exploit/reporting/SKILL.mdSecurity
3 findings: 1 critical severity, 2 high severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E006: Malicious code pattern detected in skill scripts.
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
This document contains explicit, actionable instructions and artifacts for unauthenticated remote code execution, deploying web/backdoors and reverse shells, credential theft, and internal pivoting — clearly enabling malicious activity.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill explicitly contains and instructs recording plaintext credentials (including "Str0ngP@ss2024!" in the creds JSON) and mandates saving/verbatim-reporting of captured secrets and exact commands, requiring the LLM to handle/output secret values verbatim.
W008: Secret detected in skill content (API keys, tokens, passwords).
What this means
Detected sensitive credentials directly embedded within the skill content, such as API keys, access tokens, private keys, or service-specific secrets. Secrets should never be hardcoded in plain text within skill instructions.
Why it was flagged
The JSON credential entry in exploit/creds/initial.json contains a plaintext database password ("Str0ngP@ss2024!") alongside target host/port, username, and verified:true — i.e., a captured, usable credential rather than a placeholder. The value is not a generic placeholder or obvious example and thus meets the definition of a secret to flag.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
High: the workflow requires uploading/collecting exploitation evidence (HTTP requests/responses and command outputs) into files and then persisting/linking them into findings at runtime, and those evidence texts are outsider-authored (responses/outputs from compromised targets or other parties) and can contain free-form content that the agent may read and include in LLM context.
- Repository
- PurpleAILAB/Decepticon
- Commit
0cf691e
- Audited
- Security analysis
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.