skills/michaelliv/dotskills/jira-cli/Gen Agent Trust Hub

jira-cli

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHCREDENTIALS_UNSAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION] (HIGH): Vulnerable to Indirect Prompt Injection (Category 8) due to processing untrusted data with write capabilities.\n
  • Ingestion points: Data enters the agent context through jira issue list, jira issue view, and curl responses containing ticket summaries, descriptions, and comments.\n
  • Boundary markers: Absent. No delimiters or instructions are provided to the agent to treat external Jira content as untrusted.\n
  • Capability inventory: The skill allows for significant side effects including jira issue create, edit, move, and comment add, as well as arbitrary network requests via curl to the Jira API.\n
  • Sanitization: Absent. There is no evidence of validation or filtering of content retrieved from Jira.\n- [CREDENTIALS_UNSAFE] (HIGH): The skill retrieves sensitive credentials (JIRA_API_TOKEN, JIRA_USER) from the psst global vault. This creates a risk of credential exposure or misuse if the agent is manipulated via prompt injection.\n- [EXTERNAL_DOWNLOADS] (MEDIUM): Requires the installation of ankitpokhrel/jira-cli, which is an external dependency from a non-trusted GitHub user account.\n- [COMMAND_EXECUTION] (LOW): Uses subprocesses to execute jira, psst, curl, and jq. While necessary for functionality, these tools provide the agent with local execution capabilities.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 11:36 AM