slice
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the official GitHub CLI tool (gh) to synchronize tasks with external repositories.
- Evidence: Calls to
gh issue viewto retrieve context andgh issue createto output slices are integrated into the workflow inSKILL.md. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it processes data from external sources that could contain malicious instructions.
- Ingestion points: The skill reads local file paths and fetches GitHub issue content via the
ghtool inSKILL.md(Step 1). - Boundary markers: Absent. The instructions do not define specific delimiters or directives for the agent to ignore instructions embedded within the specifications or fetched issue data.
- Capability inventory: The skill has write access to the local file system (
docs/directory) and the ability to create new issues via the GitHub API as described inSKILL.md(Step 5). - Sanitization: Absent. There is no explicit logic to filter or validate content retrieved from external files or issues before it is used to generate tasks.
Audit Metadata