strategic-roadmap
Pass
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill contains a safety instruction for handling sensitive data. It explicitly forbids the agent from copying secret values or credentials into the generated output files, directing it to only reference the file location and credential type (SKILL.md).\n- [INDIRECT_PROMPT_INJECTION]: The skill functions by ingesting and analyzing untrusted repository data, which represents a potential attack surface.\n
- Ingestion points: The skill reads project documentation (README.md, CONTEXT.md, AGENTS.md), architecture docs, ADRs, old plans, branch/bookmark notes, and issue/ticket notes (SKILL.md).\n
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the source framing logic.\n
- Capability inventory: The skill involves extensive read operations across the repository and write operations to the .agents/ROADMAP.md file (SKILL.md).\n
- Sanitization: No specific sanitization, filtering, or escaping of ingested repository content is described.
Audit Metadata