strategy
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the official GitHub CLI to interact with repositories. It executes commands to create labels, list issues, and create or edit issues using temporary body files. These commands are localized to the tunan:project issue scope and follow standard development workflows.
- [PROMPT_INJECTION]: The skill is subject to an indirect prompt injection surface as it ingests untrusted data from existing GitHub issues.
- Ingestion points: Phase 2 of the skill reads the body of an existing GitHub issue using
gh issue view. - Boundary markers: There are no specialized delimiters or system instructions used to isolate the ingested issue content from the agent's core instructions.
- Capability inventory: The skill has the capability to create and modify GitHub issues and labels via the
ghtool. - Sanitization: The skill does not sanitize or validate the content retrieved from the GitHub issue before summarizing it or incorporating it into subsequent drafts.
Audit Metadata