Find bounded, page-local related place cards using optional published-field filters. Use when an agent needs this published GoVisit evidence through HTTP for an integration or travel decision.
76%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./skills/govisit-list-related-places/SKILL.mdThe skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow POSTs a `pagePath` to the GoVisit `list_related_places` endpoint and ingests returned place cards, which are published GoVisit projections for a page the agent chose, so outsider text could reach the agent only if an outsider had published content on that selected page.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
The skill's runtime is an outbound POST to govisit.ai whose JSON responses are data, but its update instructions (lines 74-76) direct refreshing the whole skill directory from the GitHub-hosted canonical source and release package, which is installed skill material; the inhotel-io GitHub org appears to be the vendor's own, so provenance is plausibly strong, but the update path is not enforced by a verified digest in the skill itself, so I'm assigning medium under the recall-first override.
inhotel-io/govisit-toolkit
82bf7d3
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.