content-audit
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill operates entirely within the local file system using tools like Read, Glob, Grep, and Write. It does not perform any network operations, access sensitive system credentials, or employ obfuscation techniques.
- [COMMAND_EXECUTION]: The skill utilizes
GlobandGrepto discover and analyze project files (design/gdd/,assets/,src/). These operations are consistent with its primary purpose of auditing content implementation based on design specifications. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external project files (
design/gdd/*.md) to extract content counts. This represents an indirect prompt injection surface where instructions hidden in those files could theoretically influence the agent's logic. However, given the context of a local development tool scanning project-internal documentation, the risk is minimal and restricted to the local environment.
Audit Metadata