bug-triage-prep

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes bug data which may contain untrusted content from bug reports. This presents a risk of indirect prompt injection where instructions hidden in bug descriptions could manipulate the triage output.
  • Ingestion points: Bug data retrieved via list-bugs and get-task-details functions.
  • Boundary markers: No specific delimiters or instructions are used to treat bug data as untrusted text.
  • Capability inventory: No dangerous system capabilities (shell execution, network exfiltration) are associated with this skill.
  • Sanitization: No sanitization or validation of the ingested bug content is specified.
  • [SAFE]: The skill functionality is consistent with the author's (onehorizonai) stated purpose and uses vendor-specific tools without exhibiting malicious patterns like credential theft or persistence.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 12:17 PM