resilience-audit
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection because its core functionality involves the ingestion of untrusted data.
- Ingestion points: The agent is instructed to read the target application's source code and configuration files in Phase 2. In Phase 4, it interacts with a live web application, ingesting content from the DOM, console logs, and network requests, all of which could contain malicious instructions.
- Boundary markers: The skill does not define specific delimiters or instructions to the agent to treat audited content strictly as data, which may lead to the agent inadvertently following instructions embedded within the target application's code or UI.
- Capability inventory: The skill has the capability to read files from the filesystem, write reports, and use browser automation tools (
tabs_context_mcp,tabs_create_mcp) to interact with live websites. - Sanitization: There is no evidence of sanitization, escaping, or filtering of the ingested data before it is presented to the AI for analysis.
Audit Metadata