beads-trim-memories
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes "beads memories" fetched via the
bd memories --jsontool. These memories are arbitrary text strings that can influence the agent's behavior during the review process. - Ingestion points: Memories are loaded into the session context through the
bd memories --jsoncommand in Phase 1 of SKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or explicit instructions to ignore potentially malicious content within the memories being reviewed.
- Capability inventory: The skill uses
Bash,Edit, andWritetools to modify the repository and agent state based on the processed memories. - Sanitization: There is no evidence of sanitization or filtering applied to the memory content before it is processed by the agent.
Audit Metadata