launch-sub-agent
Launch an intelligent sub-agent with automatic model selection based on task complexity, specialized agent matching, Zero-shot CoT reasoning, and mandatory self-critique verification
61%
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 ./plugins/sadd/skills/launch-sub-agent/SKILL.mdW011: Third-party content exposure detected (indirect prompt injection risk).
What this means
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.
Why it was flagged
In `SKILL.md`, the outsider-authored “Task description from $ARGUMENTS” is directly embedded into the sub-agent prompt during Phase 4 (4.2 Task Body) and then dispatched in Phase 5 via the Task tool, so the runtime LLM ingests free text supplied by the caller.
- Repository
NeoLabHQ/context-engineering-kit
- Revision
23e2428
- Audited
- Security analysis
Is this your skill?
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.