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, and Grep tools.
  • 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:code and ripgrep for analyzing project code.
  • Evidence: The 'Memory Protocol' in SKILL.md directs the agent to use cat to read from internal files located in .claude/context/memory/ and to write updates to them.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 12, 2026, 08:08 PM