skills/rohitg00/agentmemory/remember/Gen Agent Trust Hub

remember

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFECREDENTIALS_UNSAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The TROUBLESHOOTING.md file contains explicit instructions for the agent to access sensitive credential files, specifically ~/.agentmemory/secret and ~/.agentmemory/.env, to facilitate a REST fallback if standard tools are unavailable. While these are vendor-specific resources, instructing an agent to manually read its own secrets increases the risk of accidental exposure or exploitation.
  • [INDIRECT_PROMPT_INJECTION]: The skill creates a significant surface for indirect prompt injection by ingesting raw user input through the $ARGUMENTS variable and storing it directly into a long-term database via the memory_save tool without any sanitization.
  • Ingestion points: The $ARGUMENTS variable in SKILL.md captures raw user input.
  • Boundary markers: There are no boundary markers or delimiters used when passing content to the memory_save tool.
  • Capability inventory: The memory_save tool writes to a persistent storage backend that is likely retrieved by a corresponding recall skill.
  • Sanitization: No filtering, escaping, or validation of user-provided content is performed, allowing potentially malicious instructions to be stored and later executed during memory retrieval.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 11:46 PM