support-tool-stack
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a local validation script
scripts/check-output.py. This script is intended to be executed by the agent to verify that the generated output meets minimum length requirements and contains necessary keywords. The script uses standard libraries and performs simple file read operations on agent-generated content. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided information such as company name, ARR, and team size to generate recommendations.
- Ingestion points: Data enters the context via user input placeholders in
templates/output-template.md(e.g., [Company], [ARR]). - Boundary markers: None explicitly defined in the templates to separate user data from instructions.
- Capability inventory: The skill primarily performs text generation and internal validation using the included Python script. It does not perform high-risk file system writes or unauthorized network operations.
- Sanitization: No specific sanitization or escaping of user-provided strings is mentioned.
- Conclusion: The risk is minimal as the ingested data is used solely for generating a text-based report within the agent's session.
Audit Metadata