holistic
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from various local project sources, creating a potential surface for indirect prompt injection where malicious instructions could be embedded in data files.
- Ingestion points: The agent is directed to read
docs/CONTEXT_MAP.md,docs/UBIQUITOUS_LANGUAGE.md,docs/contexts/*/CONTEXT.md, andCLAUDE.md, as well as explore the codebase organically. - Boundary markers: The instructions do not specify any delimiters or safety markers to differentiate between the agent's instructions and the content of the files being analyzed.
- Capability inventory: The skill utilizes file system read access and command execution (e.g.,
git log) to synthesize its orientation map. - Sanitization: There are no defined mechanisms for sanitizing or filtering instructions that might be contained within the analyzed project files.
Audit Metadata