chatto-security-review
Perform a comprehensive security review of the Chatto codebase. Launch multiple exploration agents in parallel to examine different security aspects, then have an adversarial reviewer verify and challenge the findings.
69
83%
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
Security
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 prompt explicitly tasks agents to read source code, cite exact file/line findings, and look for "secrets in code" without instructing redaction, which creates a realistic risk the LLM will output secret values verbatim.
- Repository
- chattocorp/chatto
- Commit
65f65c3
- 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.