connection-request
Pass
Audited by Gen Agent Trust Hub on May 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a vulnerability to indirect prompt injection by ingesting and processing untrusted data from web search results to generate personalized messages.
- Ingestion points: The skill retrieves contact details and 'company news' via WebSearch in Step 2 to inform message generation.
- Boundary markers: None identified; the skill directly interpolates external findings into the prompt logic for message creation in Step 3.
- Capability inventory: The skill utilizes
Writeto create local files,WebSearchto query external data, andmcp__blackboard-channel__write_to_blackboardto update system state. - Sanitization: There is no evidence of input validation, escaping, or filtering of the content retrieved from external web sources before it is used to influence agent output.
Audit Metadata