mirror-doctor
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the goldsky CLI to interact with pipeline infrastructure. It executes commands to list projects, monitor runtime performance, retrieve pipeline definitions, and perform administrative actions such as restart, resize, and delete. The use of these commands is consistent with the skill's stated purpose of pipeline maintenance.\n- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests and processes data from external CLI outputs.\n
- Ingestion points: Data enters the context via goldsky pipeline monitor and goldsky pipeline get --definition in SKILL.md.\n
- Boundary markers: The instructions do not specify the use of delimiters to separate CLI output from context.\n
- Capability inventory: The skill can execute actions including goldsky pipeline delete and goldsky pipeline apply.\n
- Sanitization: There are no instructions for sanitizing content from logs before using it to generate fix commands.
Audit Metadata