ia

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFECREDENTIALS_UNSAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The skill provides instructions for configuring and using authentication credentials, specifically referencing the configuration file path at ~/.config/ia.ini and the environment variables IA_ACCESS_KEY_ID and IA_SECRET_ACCESS_KEY.
  • [EXTERNAL_DOWNLOADS]: The skill recommends the installation of the 'internetarchive' package via 'uv' or 'pip', as well as the 'parallel' utility through system package managers. These resources are from established vendors and are necessary for the skill's primary functionality.
  • [COMMAND_EXECUTION]: The skill makes extensive use of the 'Bash' tool to execute 'ia' CLI operations for searching, downloading, and uploading content, as well as performing administrative item tasks.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the Internet Archive, creating a vulnerability surface for malicious instructions embedded in archived content. Ingestion points: Data enters the context via ia search (metadata and full-text), ia metadata, and ia download operations. Boundary markers: The skill does not provide instructions for using boundary markers or 'ignore' prefixes when processing retrieved content. Capability inventory: The agent possesses 'Bash' capabilities, allowing it to write files, modify remote metadata, and perform network uploads. Sanitization: There are no documented procedures for sanitizing or validating external content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 04:43 PM