devrel-exec-reporting
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data, such as metric frameworks, budget documents, and user-provided interview responses, to generate executive reports.
- Ingestion points: The agent is instructed to read frameworks, prior reports, and budget documents provided by the user (SKILL.md, Interview section).
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' markers when processing this external data.
- Capability inventory: The skill primarily performs text generation. It does not utilize subprocesses, network operations, or file-writing capabilities (beyond maintaining a local context file).
- Sanitization: No explicit sanitization or validation of the input data is mentioned.
- Note: While the surface for indirect injection exists, the lack of dangerous capabilities (like shell execution or data exfiltration tools) makes the risk negligible.
Audit Metadata