cs-audit
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill adheres to a read-only workflow, identifying potential issues and generating reports without the capability to modify the repository's code, which prevents unauthorized modifications.
- [SAFE]: It implements 'Guardrules' that enforce a strict scope definition phase, ensuring the agent does not perform unintended wide-scale scans.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes untrusted code from the repository.
- Ingestion points: Scans codebase files in the user-defined scope as described in Phase 2 of 'SKILL.md'.
- Boundary markers: There are no explicit instructions for the agent to ignore or delimit embedded instructions within the files it audits.
- Capability inventory: The agent can write markdown reports to the '.codestable/audits/' directory and suggest that other skills take action.
- Sanitization: No automated sanitization of scanned content is described, relying instead on the agent's internal assessment of confidence and evidence.
Audit Metadata