actionlint
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses local shell commands (
git,grep,actionlint,mise) to identify staged workflow files and validate their syntax. These operations are scoped to the repository and used for their intended purpose. - [INDIRECT_PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted data from the local environment.
- Ingestion points: The skill reads file paths from
git diff --name-onlyand diagnostic messages fromactionlint's standard output. - Boundary markers: No explicit delimiters are used to wrap tool output; the agent interprets the command results as direct context.
- Capability inventory: The skill possesses the capability to execute shell commands (
actionlint,git) and modify repository configuration viamise.toml. - Sanitization: There is no evidence of output sanitization or filtering of the content returned by the linting tool before it is processed by the agent.
Audit Metadata