distill-pr-intent-orchestrator
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands to orchestrate the workflow, including
gh pr listto retrieve pull request identifiers andseqto handle ranges of PRs. It also utilizes a custommemory-writeutility to persist data to the/memory/pr-intent/directory on EFS storage. - [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests and processes untrusted data from GitHub Pull Request content.
- Ingestion points: The skill fetches PR data using the GitHub CLI and passes PR identifiers to the
distill-pr-intentcommand, which processes the associated PR text (titles, descriptions, or comments). - Boundary markers: There are no explicit delimiters or instructions provided in this orchestrator to warn the model about potentially malicious instructions embedded within the PR content.
- Capability inventory: The skill has the capability to write files to the
/memory/filesystem via thememory-writetool. - Sanitization: The instructions do not describe any sanitization, filtering, or validation steps for the pull request data before it is processed or persisted.
Audit Metadata