guardrails
Deterministic guard layer: pre/post tool guards, prompt filter, output contracts, secrets, constitution compliance. Thin doc over hooks/scripts. Topics: constitution-compliance, input-tolerance, integrity-chain-validation, management, output-contract-enforcer, permission-fast-path, post-tool-use-validator, pre-tool-use-guard, quality-gatekeeper, secrets-sanitization, stop-validator, user-prompt-filter.
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 workflow processes incoming user prompt text (user-prompt-filter) without the agent first selecting a specific item, exposing it to indirect prompt injection.
- Repository
- JaviMontano/jm-adk-beta
- Commit
fdad39c
- 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.