security-auditor
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use
Grep,Glob, andtrivyfor scanning files and identifying vulnerabilities. These are standard security utilities and their use is consistent with the skill's stated purpose of security auditing. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its data-tracing and surface-mapping functions. Malicious instructions embedded in the source code being audited could potentially influence the agent's behavior during the audit process.
- Ingestion points: Untrusted source code and project files accessed via
GrepandGlob(SKILL.md). - Boundary markers: Absent; there are no instructions to wrap or delimit audited code to distinguish it from the agent's instructions.
- Capability inventory: The skill has access to the GitHub MCP for creating issues and can write files to
./artifacts/andscratchpad/(SKILL.md). - Sanitization: Absent; the skill does not specify any sanitization or validation of the data retrieved from the files before processing it.
Audit Metadata