hiring-signal-play
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's instructions and metadata are consistent with its stated purpose of sales outbound strategy. No evidence of prompt injection, obfuscation, or persistence was found.
- [COMMAND_EXECUTION]: The Python script
scripts/check-output.pyis a simple local utility that verifies the presence of specific sections in markdown files. It does not perform network operations or access sensitive directories. - [INDIRECT_PROMPT_INJECTION]: The skill establishes a surface for indirect prompt injection by instructing the agent to process data from external job boards and social media.
- Ingestion points: Phase 1 (SKILL.md) describes monitoring external job boards.
- Boundary markers: None.
- Capability inventory: The skill enables template generation and local file validation via script, but lacks network-write or privileged execution capabilities.
- Sanitization: None. The risk is assessed as safe due to the limited impact of the suggested actions.
Audit Metadata