compose-outreach
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is to draft personalized outreach messages based on data retrieved from legitimate services like Common Room. No evidence of malicious behavior, credential harvesting, or unauthorized network operations was found.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes untrusted data from external sources. 1. Ingestion points: Data entering through Common Room MCP tools and web search results (SKILL.md). 2. Boundary markers: Absent; there are no specific delimiters or instructions to ignore instructions embedded in the external data. 3. Capability inventory: Text generation only; the skill lacks capabilities for file modification, command execution, or network exfiltration. 4. Sanitization: Absent; the skill does not perform validation or filtering on retrieved external content.
Audit Metadata