tw-research-writing-coach
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided text for academic rewriting, creating a potential vector for instructions embedded within the text to influence agent behavior.
- Ingestion points: Raw user text is ingested at Step 4 and interpolated directly into the rewriting prompt template in
SKILL.md. - Boundary markers: The skill uses markdown headers and formatting to delineate user content, but lacks explicit instructions to the model to ignore or sanitize embedded commands within the input text.
- Capability inventory: The skill has access to
Bash,Read, andWritetools (as specified in the YAML frontmatter), which could be targets for exploitation if a prompt injection is successful. - Sanitization: No input sanitization, filtering, or validation is performed on the user-provided paragraph before processing.
Audit Metadata