skills/firecrawl/openclaw/bear-notes/Gen Agent Trust Hub

bear-notes

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill configuration specifies the installation of the grizzly CLI tool via go install github.com/tylerwince/grizzly/cmd/grizzly@latest. This is a third-party dependency required for the skill to function.
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute various shell commands using the grizzly binary, such as grizzly create, grizzly open-note, and grizzly add-text, to manage application data.
  • [INDIRECT_PROMPT_INJECTION]: The skill reads and processes content from external Bear notes, which could potentially harbor malicious instructions designed to influence the agent's behavior.
  • Ingestion points: The grizzly open-note --json command allows the agent to read note content into its context.
  • Boundary markers: The instructions do not define specific delimiters or guidelines to help the agent distinguish between its instructions and the content retrieved from notes.
  • Capability inventory: The skill can execute CLI commands and perform file system operations via shell redirection (e.g., writing tokens to files).
  • Sanitization: No sanitization, validation, or filtering of the note content is described before the data is ingested.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 07:53 PM
Security Audit — agent-trust-hub — bear-notes