writing-shape

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs legitimate file operations (reading and writing) as part of its primary function to help users draft articles. All operations are user-directed and focused on content transformation. This involves reading raw markdown data and appending processed text to an article file.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from external markdown files which could potentially contain malicious instructions intended to influence the agent's behavior.
  • Ingestion points: The input markdown file containing raw material ("the pile") referenced in SKILL.md.
  • Boundary markers: Absent; the instructions do not explicitly define delimiters or provide warnings to ignore commands or instructions embedded within the raw input material.
  • Capability inventory: The skill possesses the capability to read local files and append content to files on the disk as part of the drafting loop.
  • Sanitization: No specific sanitization, validation, or escaping of the ingested raw material is documented before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 10:24 AM
Security Audit — agent-trust-hub — writing-shape