asana
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches data from the external Asana API, which represents a potential surface for indirect prompt injection if the ingested data contains instructions designed to manipulate the AI agent's behavior.
- Ingestion points: External data enters the agent context via responses from the Asana API (routed through
https://unify.apideck.com/proxy). - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the API response.
- Capability inventory: The agent can fetch, read, and process raw data from the Asana workspace.
- Sanitization: No explicit sanitization or filtering of the downstream API responses is performed by this skill; it relies on the agent's core safety guardrails.
Audit Metadata