code-reviewer
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to analyze untrusted data provided by users, such as code diffs and files. This role inherently creates an attack surface where an attacker could embed instructions in code comments to manipulate the agent's behavior.
- Ingestion points: The skill ingests and reviews code shared by the user as part of the trigger phrases like 'review this code'.
- Boundary markers: The instructions lack explicit markers or delimiters to isolate the code being analyzed from the agent's instructional context.
- Capability inventory: The skill is limited to generating text-based review reports and does not possess capabilities like network access, file system modifications, or shell execution.
- Sanitization: No logic is provided to sanitize or filter potential instructions embedded within the reviewed material.
- [NO_CODE]: The skill is comprised entirely of Markdown instructions and does not include any scripts, executable binaries, or platform configurations that execute code.
Audit Metadata