cs-audit
Pass
Audited by Gen Agent Trust Hub on Jul 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use standard file system search and read tools (such as Grep, Glob, and file read operations) to scan project source code for potential issues.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it reads and processes untrusted data (source code and files within the repository).
- Ingestion points: Files and directories specified by the user during the Phase 2 scanning process.
- Boundary markers: None explicitly defined; the agent is directed to read the raw content of files.
- Capability inventory: The agent can read local files and write audit findings to the
.codestable/audits/directory. - Sanitization: No explicit sanitization or filtering of the scanned content is mentioned before processing.
Audit Metadata