repo-issues
Pass
Audited by Gen Agent Trust Hub on Jul 12, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists exclusively of markdown documentation and instructions for the agent to follow. It does not include any scripts (Python, JavaScript, Shell) or binary executable files.
- [DATA_EXFILTRATION]: The instructions involve reading local repository files for the purpose of architectural auditing. There are no commands or logic for transmitting data over the network or accessing sensitive global locations such as SSH keys, cloud provider credentials, or environment secret files.
- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection because it ingests untrusted data from an audited repository.
- Ingestion points: The workflow involves reading source files, configs, and project wiring (SKILL.md).
- Boundary markers: No explicit delimiters are specified to isolate untrusted file content from the agent's core instructions.
- Capability inventory: The skill has no execution capabilities, subprocess calls, or network access; it is restricted to generating a report.
- Sanitization: There are no instructions for sanitizing or escaping the content read from the repository.
Audit Metadata