stage-resolve

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the 'stagereview' package globally via npm. This tool is a resource belonging to the skill's authoring vendor, and its installation is a prerequisite for the skill's intended functionality.
  • [COMMAND_EXECUTION]: The agent is instructed to execute the 'stagereview' CLI tool for listing, showing, replying to, and resolving comments. It is also tasked with running project-specific checks such as linting, typechecking, and tests to verify code changes made in response to comments.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from review comments which could be used to influence the agent's behavior during code modification.
  • Ingestion points: Comment content is read through 'stagereview comments list' and 'stagereview comments show' as described in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions are provided to separate the user-provided comment content from the agent's operational instructions.
  • Capability inventory: The agent has the capability to modify the local filesystem (source code changes) and execute shell commands (running tests/lint and interacting with the 'stagereview' CLI) according to the instructions in SKILL.md.
  • Sanitization: The skill does not define any sanitization, validation, or filtering for the external comment content before the agent acts upon it.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 01:31 PM
Security Audit — agent-trust-hub — stage-resolve