nginx-ingress-manager
Warn
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: MEDIUMNO_CODECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (MEDIUM): High-risk attack surface due to the combination of data ingestion and powerful tool access without defined safeguards.
- Ingestion points: The skill is designed to use
ReadandGrepto process Kubernetes manifests and Ingress configurations (SKILL.md). - Boundary markers: None; there are no instructions or delimiters to prevent the agent from obeying commands embedded in the data it reads.
- Capability inventory: The skill is granted
Bash,Write, andEdittools, allowing for arbitrary command execution and file system modification. - Sanitization: No sanitization or validation protocols are described to filter malicious input from ingested files.
- [Command Execution] (LOW): The manifest explicitly requests the
Bashtool. While no malicious command strings are found in the documentation, granting shell access to an agent processing DevOps infrastructure should be reviewed for least-privilege compliance. - [No Code] (INFO): The skill consists only of a Markdown manifest. No external scripts or executable logic files were provided for analysis.
Audit Metadata