gstack-openclaw-retro

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to execute multiple local shell commands using the Bash tool to gather data from the git repository history and file system (e.g., git log, git shortlog, find, wc).
  • [DATA_EXFILTRATION]: Accesses personal information including the user's name and email via git config and commit logs. This data is used within the local context to differentiate the user from teammates and attribute contributions in the retrospective report.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from git commit messages and PR titles.
  • Ingestion points: Raw data strings from various git log commands.
  • Boundary markers: None identified; the agent parses raw command output directly.
  • Capability inventory: The skill uses the Bash, Write, and Edit tools to perform analysis and save history.
  • Sanitization: No explicit sanitization or filtering of commit message content is described prior to processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 08:50 AM
Security Audit — agent-trust-hub — gstack-openclaw-retro