signal-detector
Always-on ambient signal capture. Applies on every substantive inbound message to detect original thinking and entity mentions. Spawn as a cheap sub-agent where the harness supports it; otherwise run detection inline. Aim to never block the main response.
52
60%
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/signal-detector/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 mandates capturing and persisting the user's "exact phrasing" into brain pages and visible logs, which would force the agent to reproduce any secret/API key/password the user types verbatim in its outputs and stored pages.
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
The skill ingests outsider-authored free text from every substantive inbound message via ambient routing, extracting and persisting the user's exact phrasing into brain pages (and also reads/updates entity pages based on that text).
- Repository
- garrytan/gbrain
- Commit
055ac6c
- 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.