candid-fast-ship
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands for installation, building, testing, and post-merge hooks based on strings provided in the .candid/config.json file.
- [DYNAMIC_EXECUTION]: The skill assembles and executes shell commands at runtime using strings retrieved from the project's configuration block.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data that could potentially contain malicious instructions designed to influence agent behavior.
- Ingestion points: Git diffs analyzed for risk classification, the ship.additionalPrompt field from project configuration, and data fetched from external issue trackers.
- Boundary markers: The instructions do not specify the use of clear delimiters or warnings to ignore instructions embedded within the data being processed.
- Capability inventory: The skill is capable of executing shell commands (install, build, test, post-merge) and performing automated git actions such as creating and merging pull requests.
- Sanitization: There is no mention of sanitizing or validating ingested data before it is incorporated into prompts or used in command execution.
Audit Metadata