webhook-transforms
Generic framework for converting external events (SMS, meetings, social mentions) into brain-ingestible signals. Define a transform function, register a webhook URL, and incoming events get processed through the brain pipeline.
52
58%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Fix and improve this skill with Tessl
tessl review fix ./skills/webhook-transforms/SKILL.mdSecurity
1 high severity finding. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill requires preserving raw webhook payloads and mapping payload fields into brain pages (and writing raw payloads to dead-letter files), which forces the agent to include incoming values verbatim and therefore could expose API keys or other secrets contained in those payloads.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: 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
SKILL.md specifies that on webhook receipt the system parses an external webhook payload (outsider-authored free text/JSON) and transforms it into brain page markdown (LLM-readable text) via the “Write brain page via `gbrain put`” step, with dead-letter logging that preserves the raw payload as `_dead-letter/{timestamp}.md` on transform failure.
- Repository
- garrytan/gbrain
- Commit
3fafb69
- 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.