skills/garrytan/gbrain/capture/Gen Agent Trust Hub

capture

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest arbitrary text from users or local files and store it in a database. This constitutes a data ingestion surface that could be used for indirect prompt injection if downstream processes treat the stored content as instructions.
  • Ingestion points: Content is ingested via inline arguments, the --file flag, or standard input (--stdin) as documented in SKILL.md.
  • Boundary markers: The skill does not define specific delimiters for the ingested content, though it wraps prose in markdown frontmatter.
  • Capability inventory: The skill instructs the agent to execute the gbrain capture shell command.
  • Sanitization: No specific sanitization or filtering logic is described for the incoming text body.
  • [SAFE]: The documentation includes a security warning regarding shell history protection, advising the use of files or pipes for sensitive data instead of inline arguments. The functionality is consistent with its stated purpose of note ingestion.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 04:38 PM
Security Audit — agent-trust-hub — capture