parley
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The
scripts/ensure-bin.shscript downloads a binary from the author's GitHub repository (morphet81/scrutiny). This binary is the primary tool used by the skill to manage PR reviews. - [COMMAND_EXECUTION]: The skill executes the downloaded
scrutinybinary and utilizes shell scripts to facilitate binary installation and environment checks. These operations are core to the skill's documented functionality. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes data from external GitHub Pull Request review comments to guide automated code fixes.
- Ingestion points: The skill fetches unresolved GitHub review threads using the
parley-fetchcommand as described inSKILL.md. - Boundary markers: No explicit boundary markers or instructions directing the AI to ignore instructions embedded within the comments were found.
- Capability inventory: The skill possesses the capability to perform
git commit,git push, and post replies to GitHub PR threads using theaddPullRequestReviewThreadReplyGraphQL mutation. - Sanitization: No evidence of input sanitization, filtering, or validation of the fetched review comment content was identified in the provided scripts or instructions.
Audit Metadata