support-response-writer
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and templates for generating support replies. It does not include any scripts, executable code, or calls to external tools.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface as it processes user-provided support scenarios and customer messages. However, the risk is negligible because the agent has no capabilities (network, file access, or command execution) to exploit.
- Ingestion points: User-provided descriptions of support scenarios and customer issues in SKILL.md.
- Boundary markers: None; the instructions do not specify delimiters to separate user data from instructions.
- Capability inventory: None. The skill is limited to generating text output.
- Sanitization: None.
Audit Metadata