writing-beats
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing external raw material without adequate safeguards.
- Ingestion points: The skill processes an external markdown file of raw material as described in the
SKILL.mdfile. - Boundary markers: There are no specified delimiters or instructions to ignore potential commands embedded within the raw material provided by the user.
- Capability inventory: The skill performs file read and write operations on the local disk based on user-provided paths.
- Sanitization: The skill does not implement sanitization or validation of the content extracted from the raw material before writing it to the output file.
Audit Metadata