Skills
skills/bkircher/skills/jira-read-ticket/Gen Agent Trust Hub

jira-read-ticket

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it retrieves content from external Jira tickets (descriptions and comments) which are untrusted data sources.\n
  • Ingestion points: scripts/fetch_comments.py and scripts/fetch_description.py fetch ticket content via the Jira API.\n
  • Boundary markers: The skill does not implement boundary markers or instructions to the agent to treat the fetched content as untrusted data.\n
  • Capability inventory: The skill possesses network communication capabilities and provides instructions for shell command execution.\n
  • Sanitization: While scripts/jira.py performs markdown formatting, it does not sanitize the input for potential malicious instructions or prompt injection patterns.\n- [COMMAND_EXECUTION]: The SKILL.md file encourages the agent to use curl and jq to interact with the Jira REST API, providing examples that use environment variables for authentication.\n- [DATA_EXFILTRATION]: The skill performs network operations using urllib.request in its Python scripts and suggests curl commands to interact with external Atlassian Cloud instances based on the user-provided ATLASSIAN_URL environment variable.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 02:27 AM