generate-agent-instructions
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the repository to generate agent instructions, creating an attack surface where malicious data in the codebase could influence the agent's behavior.
- Ingestion points: Workflow Step 2 and 3 in
SKILL.mdspecify inspecting code, configuration files, scripts, and documentation across the repository. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the analyzed repository files are provided.
- Capability inventory: The skill involves deep inspection of files and the ability to write to
AGENTS.md. - Sanitization: There is no evidence of sanitization, filtering, or validation of the facts extracted from the repository before they are incorporated into the output.
Audit Metadata