jira

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes system binaries curl and jq to perform network requests to the Jira API and process the resulting JSON data. These operations are aligned with the skill's stated purpose.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it ingests untrusted data from an external source (Jira issues).
  • Ingestion points: Fetches issue summaries, descriptions, and comments via rest/api/3/search and rest/api/3/issue/{id} in SKILL.md.
  • Boundary markers: No delimiters or explicit instructions are used to distinguish external data from agent instructions.
  • Capability inventory: Includes network operations (curl) for reading, creating, and modifying resources within the Jira instance.
  • Sanitization: No sanitization or validation of the retrieved content is performed before the data is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 05:14 AM