fetch-issues
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
ghcommand-line tool to list issues and verify authentication status, and it may execute other tools defined in user configuration files. - [INDIRECT_PROMPT_INJECTION]: The skill retrieves and presents untrusted text from external issue trackers that could contain malicious instructions for the agent.
- Ingestion points: External data is ingested from GitHub issue bodies/titles, Jira records, and local markdown intent files.
- Boundary markers: The skill uses markdown headers to separate issues but lacks specific instructions to the agent to disregard instructions or commands embedded within the retrieved issue bodies.
- Capability inventory: The agent has the capability to execute shell commands and read local files as part of its primary operations.
- Sanitization: There is no evidence of sanitization, escaping, or filtering of the external issue content before it is displayed to the agent.
Audit Metadata