jira-service-desk
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the Jira Service Desk API, creating a potential surface for indirect prompt injection if the retrieved content contains adversarial instructions. 1. Ingestion points: Jira API responses retrieved through the Apideck Proxy at https://unify.apideck.com/proxy (referenced in SKILL.md). 2. Boundary markers: The instructions do not define delimiters or specific warnings to ignore embedded instructions in external data. 3. Capability inventory: The skill utilizes network capabilities to fetch and process external service data. 4. Sanitization: There is no evidence of explicit sanitization or filtering of the downstream API responses within the skill's logic.
- [SAFE]: The skill interacts exclusively with vendor-controlled domains (apideck.com) and well-known service domains (atlassian.com) for its primary operations.
- [SAFE]: Secret management is handled securely through the use of environment variables (e.g., APIDECK_API_KEY, APIDECK_APP_ID), avoiding the exposure of hardcoded credentials.
Audit Metadata