skill-researcher

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes content from external, potentially untrusted sources.
  • Ingestion points: It uses mcp__zread__read_file to ingest SKILL.md and other reference files from external GitHub repositories.
  • Boundary markers: The skill instructions do not specify the use of delimiters or 'ignore' instructions when reading and translating external files, making the agent vulnerable to instructions hidden within those files.
  • Capability inventory: The skill has the ability to search the web, read remote files, and create new directory structures/files on the local system.
  • Sanitization: There is no evidence of sanitization or validation of the fetched external content before it is processed for analysis and translation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 04:53 PM