writing-workflow
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines behaviors for processing and reviewing user-controlled markdown files.
- Ingestion points: Contents of the
ideas/anddrafts/directories (SKILL.md). - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts within the drafts.
- Capability inventory: The agent uses a
write()tool to create and modify documents based on these workflows. - Sanitization: There is no evidence of content validation or escaping for the ingested text.
Audit Metadata