issue-comments

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the tea CLI (the official Gitea/Forgejo command-line tool) to perform operations like adding and listing issue comments.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it instructs the agent to read comments from external issues which may contain malicious instructions.\n
  • Ingestion points: Data is ingested from external repositories via the tea issues <num> --comments command described in SKILL.md.\n
  • Boundary markers: The instructions do not specify any boundary markers or delimiters to help the agent distinguish between its instructions and the data being processed.\n
  • Capability inventory: The skill allows the agent to read existing comments and post new comments to the repository.\n
  • Sanitization: There is no mention of sanitizing or validating the content of the comments retrieved from the server.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 09:18 AM
Security Audit — agent-trust-hub — issue-comments