memory-review

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to read MEMORY.md and then emit report lines that include entry text and promotion/pattern snippets (e.g., "{{entry}}", "{{pattern}}"), which would require reproducing any secrets stored in memory verbatim in the output.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.70). SKILL.md Step 2–3 instructs the runtime to read MEMORY.md and any referenced topic files from the project’s auto-memory directory (user-controlled files that may contain outsider-authored text from prior sessions), then analyze that readable prose in the agent’s LLM context.