skills/wojons/skills/trust-but-verify/Gen Agent Trust Hub

trust-but-verify

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data.
  • Ingestion points: Claims are extracted from test results, coverage reports, documentation, deployment logs, and team communications as defined in SKILL.md.
  • Boundary markers: No delimiters or protective instructions are provided to the agent to isolate the extracted data from the system prompt.
  • Capability inventory: The skill involves executing shell commands via npm run to perform verification, creating a path for malicious instructions to influence system operations.
  • Sanitization: The skill does not define any methods for validating or escaping the content of the claims it processes.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 10:30 AM