contact-research
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources via the Common Room API, including professional backgrounds, social presence signals, and community engagement posts. This content is potentially attacker-controlled (e.g., via a user's social media bio) and could contain instructions meant to influence the agent's interpretation or output.
- Ingestion points: External data sources defined in
SKILL.md, specificallyScores,Recent activity,Website visits, andSparkprofiles. - Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands within the retrieved contact data.
- Capability inventory: While the skill focuses on data retrieval and interpretation, the agent context may include tools for communication or deeper system access that could be targeted by injected instructions.
- Sanitization: There are no instructions for sanitizing or filtering the content retrieved from external profile fields before it is processed by the agent.
Audit Metadata