skills/thelobbi/claude/ci-forensics/Gen Agent Trust Hub

ci-forensics

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill recommends using node -e to parse files when workflow run lists exceed token limits. This involves dynamic execution of JavaScript via the command line to process local files.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted data from external sources.
  • Ingestion points: Data is fetched via mcp__github__actions_list and mcp__github__get_job_logs in SKILL.md.
  • Boundary markers: None are present to distinguish between log content and agent instructions.
  • Capability inventory: The skill has the capability to execute shell commands (node -e) and interact with the GitHub API via MCP tools.
  • Sanitization: There is no evidence of sanitization or filtering for the content retrieved from CI logs or metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 10:14 AM
Security Audit — agent-trust-hub — ci-forensics