strategic-reading

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external source texts, such as books and articles, which serves as an entry point for potential malicious instructions intended to manipulate the agent.\n
  • Ingestion points: Ingests data from EPUB, PDF, and web articles as described in Phase 1 of the processing pipeline.\n
  • Boundary markers: The skill does not define specific delimiters or warnings to prevent the agent from following instructions embedded within the source materials.\n
  • Capability inventory: The skill includes the ability to write analysis results to the filesystem via the put_page tool, targeting directories like concepts/ and projects/.\n
  • Sanitization: There is no evidence of content sanitization or validation to filter out executable prompts or adversarial text from the ingested sources.\n- [COMMAND_EXECUTION]: The skill uses command-line utilities to process document formats.\n
  • Evidence: The workflow utilizes pdftotext -layout for PDF processing and BeautifulSoup for EPUB content extraction.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 06:18 PM
Security Audit — agent-trust-hub — strategic-reading