writing-plans

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through the processing of untrusted user specifications.
  • Ingestion points: User-provided requirements or specs are ingested to generate the implementation plan (SKILL.md).
  • Boundary markers: The skill relies on standard Markdown structure but lacks explicit delimiters or instructions to ignore commands within the ingested data.
  • Capability inventory: The skill uses tools like warcraft_plan_write and generates plans containing executable shell commands (pytest, git, curl) and code snippets.
  • Sanitization: There is no evidence of input validation or sanitization for the content of the specifications.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 11:46 PM