partner-ecosystem
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process data from external sources, including public web sweeps and internal CRM systems, which creates a potential surface for indirect prompt injection attacks where malicious instructions could be embedded in the analyzed data.\n
- Ingestion points: Untrusted data is ingested through the 'Internal data pull' (CRM records, support tickets) and 'Public sweep' (competitor directories, marketplace listings) methods described in
SKILL.md.\n - Boundary markers: The instructions do not define specific delimiters or instructions to isolate external data from the agent's core logic.\n
- Capability inventory: The agent uses tools to read CRM and web data and has the capability to generate strategic artifacts like memos and matrices based on that data.\n
- Sanitization: No explicit sanitization or content filtering is prescribed for the ingested data before it is processed.
Audit Metadata