jira-teams
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the retrieval of external data from Jira Teams, which represents an attack surface for indirect prompt injection. -- Ingestion points: The skill instructions in SKILL.md describe fetching raw responses from the Jira Teams native API. -- Boundary markers: The skill does not provide specific delimiters for the agent to isolate external data. -- Capability inventory: The skill teaches the agent to perform network requests using curl to the Apideck Proxy endpoint. -- Sanitization: No sanitization logic is provided in the skill documentation.
Audit Metadata