outside-to-issue
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes content from external Markdown files located in the
ai-docs/reviews-pr-<PR>/outside/directory to create new issue files. - Ingestion points: Markdown files (
.md) found in theoutside/directory are read and converted. - Boundary markers: The skill uses a specific Markdown template for the output, but does not define explicit delimiters or instructions to ignore embedded commands within the source review data.
- Capability inventory: Executes a shell script (
scripts/transform-outside-to-issues.sh) that performs file system read and write operations within theai-docs/directory. - Sanitization: No sanitization or escaping of the source review content is mentioned before it is interpolated into the new issue files.
- [COMMAND_EXECUTION]: The skill's primary function is to execute a local shell script (
scripts/transform-outside-to-issues.sh) with a user-supplied PR number. This relies on the local script's ability to safely handle the provided argument and perform intended file operations.
Audit Metadata