automation-audit-ops
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze external, potentially untrusted data sources which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: In SKILL.md under 'Workflow', the agent is instructed to read 'repo hooks and local hook scripts', 'GitHub Actions and scheduled workflows', 'MCP configs', and 'hook logs'.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when the agent reads or summarizes these external sources.
- Capability inventory: The skill enables the agent to use various existing capabilities (referenced via 'Skill Stack' like github-ops and workspace-surface-audit) to interact with the file system and external services.
- Sanitization: There are no explicit instructions for the agent to sanitize or validate the content of the scripts, logs, or configurations before analysis or reporting.
Audit Metadata