manage-memory

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to run local commands including ls, wc, and grep for directory indexing and line counting. It also includes a shell script loop in Step 6 to verify that markdown links in the memory files point to existing files on disk. These operations are limited to the project's local memory directory.
  • [PROMPT_INJECTION]: The skill reads and organizes existing memory files, creating a surface for indirect prompt injection from data stored in previous sessions.
  • Ingestion points: Reads contents from MEMORY.md and other .md files within the memory directory.
  • Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands within the processed memory files.
  • Capability inventory: The skill has permissions for Read, Write, Edit, Bash, Grep, and Glob tools.
  • Sanitization: No specific sanitization or escaping is performed on the content of the memory files before they are read or rewritten during the organization process.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 10:51 PM