adversarial-review
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted project files during its review workflow, creating a vulnerability surface where instructions embedded in the code could influence the agent.
- Ingestion points: Project files and external dependencies read during the 'Scope and Context' phase (Step 1 in SKILL.md).
- Boundary markers: Absent; the instructions do not specify the use of delimiters or warnings to ignore embedded instructions in the source code.
- Capability inventory: The skill possesses powerful capabilities including
Bash,Write,Read, andGreptools. - Sanitization: Absent; no explicit sanitization or escaping of the code content is mentioned before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill's instructions require the execution of shell commands for code discovery and state management.
- Evidence: The 'Search Protocol' in SKILL.md mandates the use of
pnpm search:codeandripgrepfor analyzing project code. - Evidence: The 'Memory Protocol' in SKILL.md directs the agent to use
catto read from internal files located in.claude/context/memory/and to write updates to them.
Audit Metadata