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).
35
31%
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 ./aitesis/skills/inquire/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 protocol mandates reading artifacts and surfacing collected "Evidence" (including Evidence.content) as text in Phase 2 (presenting classification + evidence), which would force the LLM to reproduce file/environment contents verbatim — a likely vector to expose API keys, tokens, or other secrets found in codebase or memory.
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 required runtime workflow for `inquire` performs Phase 1 context collection via artifact read/search and (conditionally) external fetch for `CanonicalExternal`, but it does not describe ingesting outsider-authored free text from user-generated/public feeds/queues or arbitrary sources unless explicitly selected as deterministic external evidence (and all such text is treated as first-party evidence/doc content rather than a monitored submission queue).
- Repository
- jongwony/epistemic-protocols
- Commit
e56ccd7
- 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.