writing-shape
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary functionality involves reading from and writing to user-specified local files for the purpose of article drafting. No sensitive file access, network operations, or obfuscated content were detected.\n- [PROMPT_INJECTION]: The skill processes external, untrusted content provided by the user (the 'pile' of raw material). This creates a surface for indirect prompt injection if the input files contain instructions designed to override the agent's behavior. However, the skill lacks high-privilege capabilities that would make such an attack dangerous.\n
- Ingestion points: Raw material markdown files (SKILL.md).\n
- Boundary markers: None; the agent is instructed to read the file 'end-to-end' without delimiters.\n
- Capability inventory: Restricted to reading and writing markdown files within the user's project.\n
- Sanitization: None detected beyond standard agent safety filters.
Audit Metadata