skills/heishia/ppop-code/verify/Gen Agent Trust Hub

verify

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: HIGHPROMPT_INJECTIONNO_CODE
Full Analysis
  • [NO_CODE] (LOW): The skill contains only markdown documentation (SKILL.md) and lacks functional scripts or tool definitions.
  • [PROMPT_INJECTION] (HIGH): The skill's workflow for code verification presents a high attack surface for Indirect Prompt Injection. 1. Ingestion points: Processes untrusted code changes and file diffs as defined in SKILL.md. 2. Boundary markers: Absent; there are no instructions to the agent to disregard commands or instructions embedded within the code being verified. 3. Capability inventory: The skill intends to perform 'test execution' and 'build verification', which are high-privilege actions requiring command execution. 4. Sanitization: Absent; the skill does not specify the use of sandboxed environments or input validation for the code being executed.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 17, 2026, 12:25 AM