skills/orziz/aiskills/hgsc/Gen Agent Trust Hub

hgsc

Pass

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions do not contain any prompt injection, data exfiltration, or unauthorized command execution patterns. The use of a role-play persona is within standard operational bounds for AI agents.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing untrusted data (source code and git diffs), though this is consistent with its primary purpose.
  • Ingestion points: Processes content from local files, directories, and git diff outputs provided by the user.
  • Boundary markers: The prompt does not specify the use of delimiters or escaping mechanisms to separate the code content from the review instructions.
  • Capability inventory: The agent is authorized to read local files and produce structured review text; it does not perform network operations or execute arbitrary code based on input.
  • Sanitization: No explicit sanitization of the input code is defined.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 25, 2026, 01:01 AM