writing-beats
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests raw material from external markdown files, which is a potential surface for instructions embedded in the data to influence agent behavior.
- Ingestion points: Processes a user-provided markdown file of raw material as described in
SKILL.md. - Boundary markers: The instructions do not mandate the use of delimiters or 'ignore' commands for the processed content.
- Capability inventory: Capabilities are limited to reading and appending to local files; the skill explicitly disables model invocation in the frontmatter, further limiting its ability to interact with other tools.
- Sanitization: No specific sanitization or filtering is performed on the raw material, as is typical for writing and document processing tools.
Audit Metadata