overlay-focus-scroll-contracts

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted source code from project directories (src/, app/, packages/). This creates a potential surface for indirect prompt injection if the files being audited contain malicious content designed to influence the agent's behavior.
  • Ingestion points: The skill uses rg (ripgrep) probes to read and process source code from the target directories.
  • Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore instructions embedded within the ingested code.
  • Capability inventory: The skill utilizes local file system read access via rg to perform analysis.
  • Sanitization: There is no explicit mechanism described to sanitize or validate the content extracted from search results before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 11:59 PM
Security Audit — agent-trust-hub — overlay-focus-scroll-contracts