opsx-jira-fix-queue

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for the user to manually install a missing dependency using a shell command (npx skills add FuDesign2008/open-skills...). This command references the author's own repository to provide necessary tools for the skill's operation.\n- [EXTERNAL_DOWNLOADS]: The skill suggests downloading and installing a dependency from the author's repository using the npx package runner if the requirement is not met.\n- [INDIRECT_PROMPT_INJECTION]: The skill extracts information from user input (Jira IDs and URLs) and passes it to external automation workflows without explicit sanitization or boundary markers. This creates a surface where malicious input could influence downstream tasks.\n
  • Ingestion points: User-provided strings containing Jira identifiers (SKILL.md).\n
  • Boundary markers: Absent; the skill directly enqueues parsed items without delimiters or warnings to ignore embedded instructions.\n
  • Capability inventory: The skill hands off execution to goal-driven-queue and opsx-jira-fix-workflow, which are described as tools for managing fixes and workflows, likely involving file system and network operations.\n
  • Sanitization: None described; the skill only splits the input into distinct tokens before enqueuing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 10:18 AM
Security Audit — agent-trust-hub — opsx-jira-fix-queue