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

recall

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: TROUBLESHOOTING.md instructs the agent to read local secret files (~/.agentmemory/.env and ~/.agentmemory/secret) to authenticate REST fallback requests. While it cautions against sending local-file secrets to remote URLs, it explicitly allows sending these credentials to loopback addresses (localhost, 127.0.0.0/8, or [::1]). This creates a risk if an attacker can control the local network environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and display untrusted data from the memory_smart_search tool.
  • Ingestion points: External data enters via the narrative and title fields returned by the memory_smart_search tool (SKILL.md, EXAMPLES.md).
  • Boundary markers: Absent. The skill lacks instructions to wrap retrieved memories in delimiters or warn the agent about potential instructions embedded in the memory content.
  • Capability inventory: The skill uses memory_smart_search for reading and troubleshooting steps suggest curl/HTTP requests for REST fallbacks.
  • Sanitization: Absent. There is no instruction to sanitize or filter the retrieved memory content before presenting it to the user or processing it further.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 11:45 PM