analyze-performance-intake
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from marketer connectors, pastes, and exports, which creates a surface for indirect prompt injection.
- Ingestion points: Untrusted data enters the agent context via 'marketer's connectors / exports / screenshots / pastes' as specified in the Inputs section of SKILL.md.
- Boundary markers: The instructions lack explicit boundary markers or delimiters to separate external data from system instructions, nor do they include warnings for the agent to ignore embedded instructions.
- Capability inventory: The skill has access to multiple read tools (
meta_read,social_analytics_get,ads_creative_read,video_read,campaign_read) and performs file system writes to thereports/performance/inputs/directory. - Sanitization: Although a 'Hygiene' step is defined for business logic (stripping test orders, currency alignment), there is no evidence of sanitization or escaping for potential instruction injection within the processed content.
Audit Metadata