write-a-skill

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions to run local Python validation scripts (skill_description_validator.py, skill_review_checklist_runner.py, skill_structure_validator.py). Static analysis confirms these scripts exclusively use standard libraries for file parsing and regex-based checks, with no evidence of network activity or dynamic execution of untrusted data.\n- [PROMPT_INJECTION]: A surface for indirect prompt injection exists as the skill processes user-provided requirements to generate new skill files. Evidence Chain: (1) Ingestion points: User requirements collected in SKILL.md. (2) Boundary markers: Absent in templates. (3) Capability inventory: Agent file-writing and local script execution. (4) Sanitization: Absent. The risk is minimized by the skill's mandatory review checklist and quality gates which require human verification of the output.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 10:01 PM
Security Audit — agent-trust-hub — write-a-skill