cs-feat-ff
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script located at
.codestable/tools/search-yaml.py. This script is used to query YAML-based documentation within the project repository to retrieve architectural constraints and historical learnings during the feature implementation process. - [DATA_EXPOSURE_AND_EXFILTRATION]: The skill requires access to and reading of project-level metadata and documentation files within the
.codestable/directory, includingattention.md, architecture docs, and requirement specifications. These files provide context for the agent's actions. - [INDIRECT_PROMPT_INJECTION]: The skill ingests project documentation and search results to guide its logic, which presents a surface for indirect prompt injection if those files contain untrusted content.
- Ingestion points: Documentation files located in
.codestable/architecture/,.codestable/compound/, and.codestable/requirements/. - Boundary markers: Absent; the instructions do not provide explicit delimiters or prompts to the agent to disregard instructions that might be embedded within the project's own documentation.
- Capability inventory: Local shell execution (Python script), file system modification (creating ff-note files), and project-level git operations (scoped-commit).
- Sanitization: Absent; the information retrieved from documentation files is used directly to inform implementation and decision-making.
Audit Metadata