writing-shape

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates entirely on local markdown files provided by the user. It reads input data ('the heap') and writes/appends to an output file ('the article'). These operations are consistent with the skill's stated purpose and do not involve sensitive system files or network exfiltration.
  • [PROMPT_INJECTION]: There is a potential for indirect prompt injection since the skill ingests untrusted markdown content from external files. If these files contain malicious instructions, they could attempt to influence the agent's behavior.
  • Ingestion points: Reads user-provided markdown files referenced in the instructions.
  • Boundary markers: None specified for the input data.
  • Capability inventory: File read and write access for local markdown documents.
  • Sanitization: No explicit sanitization of input content is mentioned.
  • Mitigation: The risk is mitigated by the skill's design, which requires a step-by-step interactive 'grilling' session where the user must choose openings and approve every paragraph added to the document.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 01:25 AM
Security Audit — agent-trust-hub — writing-shape