prompt-injection

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill establishes an indirect prompt injection surface by reading and processing external content from a user-provided target directory. While intended for defensive analysis, the agent could potentially be influenced by malicious instructions embedded within the files it is tasked to audit.
  • Ingestion points: Files within the directory specified by the target-file-or-directory argument are read using the Read, Grep, and Glob tools.
  • Boundary markers: The instructions do not specify the use of delimiters or protective headers to prevent the model from obeying instructions found within the audited data.
  • Capability inventory: The skill utilizes file system inspection tools (Read, Grep, Glob) as defined in its allowed-tools metadata.
  • Sanitization: There is no mechanism described for sanitizing or filtering the content retrieved from the target files before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 01:07 AM
Security Audit — agent-trust-hub — prompt-injection