The Agent Skills Directory

[UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill executes standard development tools (e.g., ESLint, Ruff, Cargo, Go) via the Bash tool and npx to perform code validation tasks. This behavior is consistent with its stated purpose and targets well-known utilities from official registries.
[DATA_EXPOSURE_AND_EXFILTRATION]: No patterns of unauthorized data access or external transmission were found. The skill references standard configuration paths for model settings, which is appropriate for its integration features.
[PROMPT_INJECTION]: The instructions focus on tool workflows and orchestration. No attempts to bypass safety filters or extract system prompts were detected.
[INDIRECT_PROMPT_INJECTION]: The skill processes project files and tool outputs during the quality gate process.
Ingestion points: Reads files and directory structures to identify languages and run linters.
Boundary markers: No explicit instructions are provided to the agent to ignore embedded instructions in the processed data.
Capability inventory: The skill has access to Bash, LSP, Read, and Glob tools.
Sanitization: No explicit sanitization or validation of the processed code content is described. Note: This is considered a standard operational risk for development tools and does not indicate malicious intent.

gates