review-code
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local shell commands such as
jq,fd,cat, andlsto interact with project configuration and files. These operations are standard for development automation tools. - [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it ingests and interprets untrusted content from specification files and source code.
- Ingestion points: The skill reads project specifications from the
specs/directory and various implementation files. - Boundary markers: The instructions do not specify the use of delimiters or provide the agent with guidance to ignore embedded instructions in the content being reviewed.
- Capability inventory: The skill has the ability to execute local shell commands, write to the
REVIEWERS.mdfile, and invoke other internal skills (spex:deep-review,spex:evolve). - Sanitization: The skill does not perform any explicit validation or sanitization of the input file content before processing it.
Audit Metadata