Validate an existing Sim integration (tools, block, registry, and resolved-secret/model-input boundaries) against the service's API docs and Sim execution conventions
75%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Critical
Do not install without reviewing
Fix and improve this skill with Tessl
tessl review fix ./.agents/skills/validate-integration/SKILL.mdDetected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
The skill is a developer audit guide, but it tells the agent to commit regenerated diffs for other integrations, including unrelated stale-page catch-up, and to fix everything without asking, which alters the user's work beyond the requested integration.
The 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 fetches the service's API documentation via WebFetch or Context7 (SKILL.md:14, 46-48), and the docs URL is user-supplied, so it may point to an arbitrary web page; this is an agent-initiated fetch of outsider-capable content, which is low rather than medium because no monitored inbox or feed is read.
simstudioai/sim
edf5f0a
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.