skills/mizchi/skills/security-expert/Gen Agent Trust Hub

security-expert

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from the repository, including security scan JSON files and raw source code.
  • Ingestion points: Accesses files at <client-repo>/.frontend-review/report/latest/raw/security.json and deps.json, as well as source code containing dangerouslySetInnerHTML or environment variable usage.
  • Boundary markers: Absent. The instructions do not define delimiters to separate the skill's instructions from the content of the files being reviewed.
  • Capability inventory: Includes file system read access for the entire repository and file system write access to the .frontend-review subdirectory.
  • Sanitization: No explicit sanitization or instruction to ignore embedded commands within the analyzed code is present.
  • [COMMAND_EXECUTION]: The skill requires the agent to execute file system operations (read/write). These operations are restricted to the local workspace and are necessary for its documented function as a codebase reviewer.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 03:37 AM
Security Audit — agent-trust-hub — security-expert