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 -eto 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_listandmcp__github__get_job_logsinSKILL.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