writing-assistant
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user text for rewriting and editing tasks without implementing safety boundaries, which could allow malicious instructions within that text to influence the agent's behavior.
- Ingestion points: User-provided text ingested during the 'Read the original text' step defined in SKILL.md.
- Boundary markers: None identified; the skill lacks delimiters or specific instructions for the agent to disregard instructions found within the input text.
- Capability inventory: The skill is restricted to text generation and does not have access to sensitive tools, network operations, or file system writes.
- Sanitization: No input sanitization or validation mechanisms are present to filter content from the user.
Audit Metadata