skill-lifeguard

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local validation scripts (python3 ./scripts/validate_skills.py and python3 ./scripts/audit_skill_quality.py). This is a standard operation for developer-focused skills to ensure repository integrity.
  • [PROMPT_INJECTION]: The skill processes content from other skill files, creating a potential surface for indirect prompt injection. * Ingestion points: Processes target SKILL.md and reference files during the audit workflow. * Boundary markers: No explicit delimiters are used to separate audited content from instructions. * Capability inventory: Executes local scripts and modifies skill files. * Sanitization: No explicit sanitization of ingested content is performed, though the skill uses structured output templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 01:59 AM
Security Audit — agent-trust-hub — skill-lifeguard