skills/etalab-ia/dragster/search/Gen Agent Trust Hub

search

Warn

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires installation of the @tobilu/qmd Node.js package from a public registry. This dependency is not provided by a recognized trusted organization or the skill's author.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute search queries via the command qmd query "<query>". This template is vulnerable to command injection if the agent interpolates user input into the query without proper shell escaping.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection. It retrieves excerpts from external documents and integrates them into the agent's context.
  • Ingestion points: Data is ingested from document excerpts retrieved via search results in SKILL.md.
  • Boundary markers: There are no delimiters or specific instructions to the agent to treat the retrieved content as untrusted.
  • Capability inventory: The agent has access to the Bash tool, which could be exploited if malicious instructions are present in the documents.
  • Sanitization: No sanitization or validation of the retrieved excerpts is performed before they are processed by the agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 31, 2026, 11:40 AM