santa-method
Multi-agent adversarial verification with convergence loop. Two independent review agents must both pass before output ships. Use when output must clear two independent adversarial reviewers before it ships.
66
80%
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
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 reviewer prompts require quoting and "record[ing] findings verbatim" and to "cite the exact problem" while being fed the original spec and output, so if those contain API keys, passwords, or tokens the reviewers are instructed to reproduce them in their structured JSON—creating a high-risk secret-exfiltration path.
- Repository
- affaan-m/ECC
- Commit
07756ce
- 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.