audit-agent-context
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses standard version control commands to resolve the repository structure and track file status.
- Evidence:
git rev-parse --show-toplevel,git ls-files,git statusin SKILL.md. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from documentation files within the repository which could contain malicious instructions.
- Ingestion points: Reads local
AGENTS.mdandCLAUDE.mdfiles (SKILL.md). - Boundary markers: Absent; the skill does not specify delimiters for data extracted from these files.
- Capability inventory: Extremely limited; findings are restricted to read-only filesystem checks and git metadata queries.
- Sanitization: Absent; the skill reports file content directly as evidence for discrepancies.
Audit Metadata