paper-summary

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external paper notes which may contain embedded instructions designed to override the agent's behavior during the summarization process.
  • Ingestion points: The skill reads the full content of files located at $OBSIDIAN_VAULT/papers/notes/ and $OBSIDIAN_VAULT/Paper_Index.md.
  • Boundary markers: Absent. The skill does not instruct the agent to use delimiters or to disregard instructions found within the ingested note content.
  • Capability inventory: The skill possesses file read access to the vault and file write access to the $OBSIDIAN_VAULT/knowledge/Summary/ directory.
  • Sanitization: Absent. There is no requirement to filter or sanitize the content of the notes before they are processed by the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 09:16 AM
Security Audit — agent-trust-hub — paper-summary