code-explainer
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted code snippets from users, which can be used to deliver malicious instructions to the agent.\n
- Ingestion points: Input field for 'the code' (snippet or file path) defined in SKILL.md.\n
- Boundary markers: Absent; the instructions do not utilize delimiters or explicit instructions to ignore commands embedded within the code content.\n
- Capability inventory: The skill does not restrict tools in its frontmatter, meaning the agent retains default access to system capabilities (shell, file system, network) that could be targeted by an injection.\n
- Sanitization: Absent; the skill does not perform any validation or filtering on the provided code before processing it.
Audit Metadata