bear-map

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes shell commands using the scimaster-cli tool to perform academic searches and verify the CLI's installation status. This is a functional requirement for the skill's data retrieval tasks.
  • [EXTERNAL_DOWNLOADS]: The skill retrieves academic metadata and paper abstracts from the SciMaster service and directs users to install its CLI dependency via the public npm registry. These sources are consistent with the skill's stated purpose of scientific research.
  • [PROMPT_INJECTION]: The skill processes paper abstracts retrieved from external sources, which constitutes an indirect prompt injection attack surface. Ingestion points: Abstracts are ingested from search results in Step 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used when the agent processes the abstract content. Capability inventory: The agent has access to shell commands and file writing capabilities. Sanitization: The skill does not define specific sanitization or filtering logic for external content before it is included in reports or HTML visualizations.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 01:39 PM
Security Audit — agent-trust-hub — bear-map