event-networking
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains no executable scripts, obfuscated code, or unauthorized network requests. Its content is restricted to instructional markdown and communication templates.
- [INDIRECT_PROMPT_INJECTION]: The skill describes a workflow that involves gathering and processing untrusted data from external sources, which is a common vector for indirect prompt injection.
- Ingestion points: SKILL.md instructs the agent to read local context from .agents/sales-context.md and gather data from attendee lists, sponsor portals, and scraped speaker/exhibitor pages.
- Boundary markers: No specific delimiters or safety instructions are provided to the agent to distinguish between the skill's instructions and the potentially malicious data found in external sources.
- Capability inventory: SKILL.md directs the agent to use other specialized skills, such as lead-research, to analyze the ingested data.
- Sanitization: There are no instructions for sanitizing or validating the data collected from external event platforms.
Audit Metadata