writing-shape
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted raw material (markdown files, transcripts, or prose) provided by the user.
- Ingestion points: The agent is instructed to "Read the pile" (the input file) in full to form a sense of what's in it.
- Boundary markers: There are no instructions defining clear boundaries or telling the agent to ignore any potential commands or system-level instructions embedded within the raw source material.
- Capability inventory: The skill allows the agent to read from and append content to files on the local filesystem.
- Sanitization: No sanitization, escaping, or validation logic is defined to prevent instructions hidden in the input pile from being executed or influencing the shaping of the output article.
Audit Metadata