manage-portal-members-and-prospects
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external users (prospects and portal members) and has the capability to perform state-changing administrative actions.\n
- Ingestion points: Untrusted data enters the agent context via the getProspects (Step 3) and getCommunityUsers (Step 6) operations in SKILL.md.\n
- Boundary markers: Absent. The skill does not define specific delimiters or instructions to ignore embedded commands within user-supplied fields.\n
- Capability inventory: The skill can perform network operations including approveProspect, rejectProspect, addGroupMappingToUser, and disableCommunityUser (all in SKILL.md).\n
- Sanitization: Absent. There is no explicit sanitization or validation of the data retrieved from the prospect or member lists before it is used in subsequent operations.
Audit Metadata