deal-closer-playbook
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data retrieved via the WebSearch tool, which could potentially contain malicious instructions. Ingestion points: The company research phase in SKILL.md and references/intelligence-gathering.md uses WebSearch to collect news, financial signals, and social media data. Boundary markers: There are no explicit instructions or delimiters defined to isolate or sanitize external content from the agent's internal logic. Capability inventory: The skill utilizes WebSearch, Read, Write, and Bash tools. Sanitization: No sanitization or verification steps are present for data ingested from external web sources before it is written to the output file deal-playbook.md.
Audit Metadata