Cta Skill
Analysis
This is a coherent CTA transit helper that uses official CTA APIs, optional CTA API keys, and a local public transit-data cache; the main thing to notice is that some prerequisites are under-surfaced in registry metadata.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
requires:\n bins: ["node", "unzip"]\n env: ["CTA_TRAIN_API_KEY", "CTA_BUS_API_KEY"]\n install:\n - ... command: "npm install --prefix $SKILL_DIR"
SKILL.md discloses runtime binaries, API-key environment variables, and an npm setup step that are not surfaced in the registry metadata.
On first use, run `node scripts/cta.mjs refresh-gtfs` to download and extract the static GTFS data ... to `~/.cta/gtfs/`.
The skill includes a user-directed command that downloads and extracts public CTA schedule data locally; this is aligned with route/stop lookup functionality.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
Environment variables: CTA_TRAIN_API_KEY, CTA_BUS_API_KEY ... External endpoints: https://lapi.transitchicago.com ... https://www.ctabustracker.com
The skill uses CTA-specific API keys and sends requests to CTA-operated endpoints, which is expected for real-time train and bus data but still involves delegated API access.
