fit-pathway

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx to download and execute the fit-pathway and fit-map packages from the NPM registry. This is a standard mechanism for executing the vendor's CLI utilities.
  • [COMMAND_EXECUTION]: The documentation provides numerous examples of shell commands used to interact with the career progression data, such as npx fit-pathway build and npx fit-pathway agent <discipline>. These commands are used to process local YAML data and generate documentation or configuration files.
  • [REMOTE_CODE_EXECUTION]: The fit-pathway update command supports a --url flag, allowing the tool to fetch updates from a remote source. This is an administrative feature for keeping the engineering standard data synchronized.
  • [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection because it processes YAML data to generate agent profiles and instructions.
  • Ingestion points: Local YAML files (e.g., standard.yaml, levels.yaml, stages.yaml) located in the ./data/pathway/ directory as described in SKILL.md.
  • Boundary markers: The documentation does not specify the use of delimiters or ignore-instructions markers in the generated agent profiles.
  • Capability inventory: The skill has the capability to write files and execute shell commands via the CLI tool.
  • Sanitization: No data sanitization or validation of the input YAML content is explicitly mentioned in the skill instructions prior to profile generation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 04:33 AM
Security Audit — agent-trust-hub — fit-pathway