Build, publish, and verify a Deepline Play as a durable state machine over Customer DB tables, including a small paid pilot. Invoke this skill explicitly when the user asks to build an engine.
77%
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 ./skills/deepline-engine/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's purpose is a bounded engine build with disclosed caps and a disclosed pilot. Ambiguity remains because it tells the agent to skip approval during publication and to keep execution traces out of the default deliverable, which is mild concealment of the skill's own activity, so I rate it medium under the recall-first override rather than no.
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 reads Deepline Play search results and descriptions (workspace and prebuilt Plays, per SKILL.md line 46), and the paid pilot runs live transitions whose provider results the agent reviews, but outsiders cannot post into these sources and the agent must actively select or run them, so this is low exposure.
getaero-io/gtm-eng-skills
e8d12d1
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.