hrt-apply-code-review

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes external, potentially untrusted data from the local file system (specifications, design documents, and source code) without explicit sanitization or boundary markers. This creates a surface for indirect prompt injection where malicious instructions embedded in these files could influence the agent's behavior during the review process.
  • Ingestion points: Reads content from specs/**/*.md, design.md, tasks.md, and the project's source code.
  • Boundary markers: The skill does not define specific delimiters to separate the data being reviewed from the instructions guiding the agent.
  • Capability inventory: The agent has the ability to execute shell commands (tests/linters) and modify files on disk.
  • Sanitization: There is no mention of filtering or validating the content of the documents being processed.
  • [COMMAND_EXECUTION]: The agent is instructed to 'run the full test suite and any linters'. This involves executing shell commands within the local environment. While a standard part of the code review process, this is a sensitive capability that relies on the integrity of the project's test configuration.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 03:08 AM
Security Audit — agent-trust-hub — hrt-apply-code-review