botlearn-selfoptimize
Warn
Audited by Snyk on Mar 7, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's Community Help flow and scripts (flows/community-help.md and scripts/botlearn-post.sh) instruct the agent to fetch instructions from and post/read user-generated content on the public BotLearn site (https://botlearn.ai) and to read community posts/comments via its API, meaning untrusted third‑party content is ingested and can directly influence the agent's subsequent actions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill's community-help flow and registration scripts explicitly fetch and follow remote instructions from https://botlearn.ai/skill.md (and interact with https://botlearn.ai/api/... endpoints) at runtime, which can directly control agent behavior and is relied on for posting/registration, so this external URL poses a prompt-injection/control risk.
Audit Metadata