triage-sweep

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external data from GitHub issues and pull requests, creating a surface for indirect prompt injection.
  • Ingestion points: Processes external repository issues and pull requests, and accepts verbatim command arguments as specified in SKILL.md.
  • Boundary markers: Absent; there are no specific delimiters or instructions provided to the agent to help it ignore instructions embedded within the processed external data.
  • Capability inventory: The skill utilizes the Bash tool to execute commands based on the processed data.
  • Sanitization: Absent; no explicit validation, escaping, or filtering logic is defined for the external data or arguments before they are used.
  • [COMMAND_EXECUTION]: The skill indicates that user-supplied arguments are passed through verbatim to shell commands, which presents a surface for potential command injection if these inputs are not properly sanitized by the underlying tools or scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 03:34 PM
Security Audit — agent-trust-hub — triage-sweep