cs-feat-ff
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a local utility script
python .codestable/tools/search-yaml.pyto search project-specific documentation (learning, decisions, tricks) within the.codestable/directory. The command is used to contextualize the AI agent before code implementation. - [DATA_EXFILTRATION]: Analysis confirms no network activity or data exfiltration. The skill interacts solely with the local file system to read project docs and write implementation notes.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests untrusted data from local project files (e.g.,
.codestable/documentation) into the agent's context. However, this is intended behavior for a documentation-aware development tool and is considered safe within the local project environment.
Audit Metadata