skills/tstelzer/skills/writing-plans/Gen Agent Trust Hub

writing-plans

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • Prompt Injection (SAFE): No malicious instructions or attempts to bypass safety filters were detected in the prompt text.
  • Indirect Prompt Injection (LOW): The skill is designed to process external project specifications, which introduces a surface for indirect prompt injection. [Ingestion points]: User-provided project requirements as described in the frontmatter. [Boundary markers]: None present in the template. [Capability inventory]: The skill specifies writing files to the local repository. [Sanitization]: None specified. The risk is categorized as low because the output is documentation intended for human review.
  • Remote Code Execution (SAFE): This is a 'no-code' skill; it contains no scripts, external downloads, or dynamic execution patterns.
  • Data Exposure (SAFE): No credentials, private keys, or unauthorized data access patterns were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:36 PM