skills/morphet81/scrutiny/parley/Gen Agent Trust Hub

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.sh script 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 scrutiny binary 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-fetch command as described in SKILL.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 the addPullRequestReviewThreadReply GraphQL 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
Risk Level
SAFE
Analyzed
Aug 3, 2026, 02:57 AM
Security Audit — agent-trust-hub — parley