timeline-report

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts (memory_store.py and vector_search.py) to retrieve and process session history data. These scripts are invoked via the command line to generate timelines and perform vector searches.
  • [PROMPT_INJECTION]: The skill accesses historical interaction data from a local database (~/mnt/.claude/.cowork-mem/memory.db), creating a surface for indirect prompt injection if previous logs contain malicious instructions intended to manipulate the reporting output.
  • Ingestion points: Data is read from ~/mnt/.claude/.cowork-mem/memory.db for both timeline generation and vector search.
  • Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious content within the ingested memory.
  • Capability inventory: The skill can execute shell commands (running Python scripts) and perform file system writes (exporting reports to /tmp).
  • Sanitization: There are no explicit instructions for the scripts or the agent to sanitize the data retrieved from the database before inclusion in the final report.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 01:40 PM
Security Audit — agent-trust-hub — timeline-report