cmd-proofread
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted user-provided text ('the full post') and has instructions to 'edit the file directly'. This pattern exposes the agent to indirect prompt injection if the text contains malicious instructions.
- Ingestion points: The agent is instructed to read the full post content within SKILL.md.
- Boundary markers: There are no markers or delimiters specified to isolate user content from the agent's instructions.
- Capability inventory: The skill specifies that the agent should 'edit the file directly' and 'apply all... fixes in place', which includes modifying text and links.
- Sanitization: No sanitization or verification of the input text is performed before it is used to drive file-writing operations.
Audit Metadata