app-store-changelog

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local shell script scripts/collect_release_changes.sh to retrieve git commit logs and file changes. This script is a vendor-provided resource necessary for the skill's primary functionality.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted data from git commit history. * Ingestion points: Git commit messages and lists of touched files gathered via the collection script. * Boundary markers: No explicit delimiters or boundary markers are defined to prevent the agent from executing instructions found in commit messages. * Capability inventory: Subprocess execution of local scripts and LLM-based summarization of external content. * Sanitization: There is no evidence of data sanitization or filtering to remove potential malicious instructions from the git history before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 05:13 AM