signal-scoring
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external prospecting data, including account lists and buying signals (hiring, funding, tech stack changes), which represents a potential surface for indirect prompt injection. However, the risk is negligible as the skill lacks high-privilege capabilities such as network access, shell execution, or file-write operations that could be exploited via malicious input.\n
- Ingestion points: Target account lists and signal data descriptions processed in Phase 2 and 3 of SKILL.md.\n
- Boundary markers: None explicitly defined for untrusted lead data.\n
- Capability inventory: Minimal; limited to a local file-read script (scripts/check-output.py) used for content validation.\n
- Sanitization: Not implemented for external lead or signal descriptions.
Audit Metadata