team-memory-search

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill instructs the agent to read and follow 'Reuse' actions from files located in the .agents/project-memory/entries/ directory. This creates a surface for indirect prompt injection, where malicious instructions could be embedded in the project memory to influence the agent's behavior.
  • Ingestion points: .agents/project-memory/entries/ and .agents/project-memory/policy.md (SKILL.md)
  • Boundary markers: Absent; there are no explicit delimiters or instructions provided to the agent to ignore or sanitize embedded instructions within the retrieved memory content.
  • Capability inventory: Reading local files and executing steps described as 'Reuse' actions (SKILL.md).
  • Sanitization: Absent; the skill does not mention any validation or filtering of the data retrieved from the memory store.
  • [NO_CODE]: The skill consists entirely of markdown instructions and YAML configuration. No executable scripts or binaries are distributed with this skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 08:01 PM
Security Audit — agent-trust-hub — team-memory-search