Places Search
Analysis
This appears to be a straightforward places/geocoding skill that uses a disclosed Camino API key and sends user-provided place searches to Camino’s API.
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.
Install all available skills ... npx skills add https://github.com/barneyjm/camino-skills
The installation guidance includes a remote GitHub install and suggests installing the entire companion skill suite. This is user-directed and disclosed, but it can broaden the agent's installed capabilities beyond this single Places skill.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
-H "X-API-Key: $CAMINO_API_KEY"
The script authenticates to Camino using the user's CAMINO_API_KEY. This is expected for the stated API-backed place lookup purpose, but the key represents account/quota authority and should be protected.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
-d "$INPUT" \
"https://api.getcamino.ai/search" | jq .The script sends the user-provided JSON search input to Camino's external API. This is disclosed and purpose-aligned, but place/address searches can reveal sensitive location interests.
