agent-data-build

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external, untrusted websites which could contain malicious instructions.
  • Ingestion points: Untrusted website content is fetched via the agent-data parse command using the SOURCE_URL variable in SKILL.md.
  • Boundary markers: There are no instructions to use delimiters or ignore instructions that may be found within the retrieved web content.
  • Capability inventory: The skill executes shell commands (agent-data CLI), writes to local files (api-task.md), and makes network requests.
  • Sanitization: The instructions do not specify any validation or sanitization steps for the data retrieved from the SOURCE_URL before the agent acts on it.
  • [COMMAND_EXECUTION]: The skill heavily utilizes shell commands to interact with the agent-data CLI tool.
  • Evidence: Commands like agent-data parse "$SOURCE_URL" --task "$(cat api-task.md)" and agent-data parse events are used throughout the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 07:59 PM