discovery
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: 1. Ingestion points: The skill reads project documentation from docs/, .great_cto/, and README* files, and processes outputs from tools like grep and bd search. 2. Boundary markers: Absent; no specific delimiters or instructions to ignore instructions embedded within the discovered files are provided. 3. Capability inventory: The skill utilizes Read, Grep, Glob, and Bash (git and bd search) tools for information gathering. 4. Sanitization: Absent; the skill does not specify any validation or filtering of content retrieved from the file system or tool outputs.
Audit Metadata