Agentic Actions Auditor
by Trail of Bits OrgOfficialSkill · in Security Research
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations — detects prompt injection via env var patterns and dangerous sandbox configs.
This skill has been submitted and is awaiting security assessment.
Required Permissions
Tags
Repository data will be available after the next enrichment run.
Similar Skills
Semgrep Scanner
Runs Semgrep static analysis with parallel subagents — full ruleset and high-confidence security scan modes with Semgrep Pro cross-file taint analysis.
CodeQL
Scans codebases for security vulnerabilities using CodeQL interprocedural data flow and taint tracking — supports full and important-only scan modes.
Atheris Python Fuzzer
Coverage-guided Python fuzzer based on libFuzzer — fuzzing pure Python code and Python C extensions.