candid-validate-standards
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFE
Full Analysis
- COMMAND_EXECUTION (SAFE): The skill uses
lsto check for the presence of standard linter configuration files. This is a read-only check of file existence and does not involve executing the files themselves or using unsanitized user input in a way that allows arbitrary command execution. - DATA_EXPOSURE (SAFE): The skill reads the content of
Technical.mdto perform its analysis. While it accepts a path argument, it only processes markdown-style lists and headers and does not target sensitive system files or credentials. - INDIRECT_PROMPT_INJECTION (SAFE): The skill ingests untrusted data from a markdown file. 1. Ingestion points: Technical.md (Step 3). 2. Boundary markers: None. 3. Capability inventory: File system enumeration via
ls(Step 2). 4. Sanitization: Rule extraction is limited to specific markdown line prefixes.
Audit Metadata