inquire
Infer context insufficiency before execution. Surfaces uncertainties through information-gain prioritized inquiry when AI infers areas of context insufficiency, producing informed execution. Type: (ContextInsufficient, AI, INQUIRE, Prospect) → InformedExecution. Alias: Aitesis(αἴτησις).
27
17%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./aitesis/skills/inquire/SKILL.mdSecurity
2 findings — 1 high severity, 1 medium severity. 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
Insecure credential handling detected (high risk: 1.00). The protocol explicitly instructs the agent to Read/Grep codebase, memory and history and to present collected "Evidence" in Phase 2 (including targeted read-only/lookups and observation results), which can include verbatim config values or tokens from files—so it may require outputting secret values directly, creating exfiltration risk.
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: 0.90). The skill's Phase 1 context-collection explicitly performs WebSearch/WebFetch (the "CanonicalExternal" / `source: "web:{url}"` flows described under Phase 1 Ctx and "Web context") to gather external docs (RFCs, vendor API pages) that the agent reads and uses to classify uncertainties and drive follow-up actions, exposing it to untrusted third-party web content.
- Repository
- jongwony/epistemic-protocols
- Commit
a1acc87
- 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.