article-extractor
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends installing third-party tools such as @mozilla/readability-cli, reader-cli, and trafilatura from public registries (NPM and PyPI) to perform text extraction.
- [COMMAND_EXECUTION]: The provided instructions include bash command sequences that interpolate user-supplied URLs and extracted metadata (like article titles) into shell pipelines. This pattern requires careful handling by the agent to prevent command injection if variables are not properly escaped before shell execution.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external websites, which could contain malicious instructions.
- Ingestion points: External web content downloaded via curl, reader, or trafilatura tools.
- Boundary markers: The skill does not implement delimiters or specific instructions to the agent to ignore potential instructions embedded within the extracted article content.
- Capability inventory: The skill utilizes 'Bash' for processing and 'Write' for saving files, which could be targeted by successful injection.
- Sanitization: While the extraction tools strip HTML tags, the resulting plain text content is not further sanitized for potential prompt injection patterns.
Audit Metadata