grok-repo

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes a local shell script (scripts/archaeology.sh) to perform analysis on a repository's git history. The script exclusively uses standard, read-only command-line utilities including git, grep, awk, sort, and uniq to generate a digest of commits, authors, and file churn.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and summarize data from external repositories, including source code and git commit messages. This creates a potential surface for indirect prompt injection.
  • Ingestion points: The agent reads file content and git logs via the git archaeology section in SKILL.md and the scripts/archaeology.sh script.
  • Boundary markers: The instructions do not define specific delimiters or "ignore" instructions for the ingested repository content.
  • Capability inventory: The skill has the ability to execute shell commands via scripts/archaeology.sh and direct git commands (git show, git log, git blame) as described in SKILL.md.
  • Sanitization: There is no explicit sanitization or filtering of the repository data before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 06:06 PM
Security Audit — agent-trust-hub — grok-repo