publish-issues

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill reads and processes external, potentially untrusted data to generate tracker issues.
  • Ingestion points: Processes conversation history, repository specification files, and external issue bodies/comments via URLs provided by the user.
  • Boundary markers: The instructions do not define specific delimiters or "ignore previous instruction" wrappers when reading external references to prevent data from being interpreted as instructions.
  • Capability inventory: The skill is capable of reading codebase files, writing to local scratch files, and publishing issues to remote trackers such as GitHub, GitLab, and Linear.
  • Sanitization: There are no explicit instructions to escape, filter, or validate the content retrieved from external sources before it is used to draft new issues.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 04:13 AM
Security Audit — agent-trust-hub — publish-issues