calibrate
Context-adaptive delegation calibration through scenario-based interview. Detects execution context to select entry mode (Solo/TeamAugment/TeamRestructure) and produces a DelegationContract. Type: (DelegationAmbiguous, AI, CALIBRATE, TaskScope) → CalibratedDelegation. Alias: Epitrope(ἐπιτροπή).
56
35%
Does it follow best practices?
Impact
93%
1.97xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./epitrope/skills/calibrate/SKILL.mdSecurity
1 medium severity finding. This skill can be installed but you should review these findings before use.
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
Third-party content exposure detected (high risk: 0.80). The skill's Domain Taxonomy in references/operational-guide.md explicitly includes "Exploration" with "web research" as an example action, and the protocol phases (Phase 1/2 and Domain Priority) require calibrating/performing applicable domains, so the agent is expected to read public web content (untrusted third‑party content) as part of its workflow which can influence decisions and tool use.
- Repository
- jongwony/epistemic-protocols
- Commit
d60dcf0
- 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.