reflect-skills-from-memory
Warn
Audited by Snyk on Jul 7, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). SKILL.md instructs the agent to read per-project memory files (
$HOME/.claude/projects/.../memory/MEMORY.mdandfeedback_*.md/project_*.md) at runtime, and those memory files are outsider-authored free text relative to the skill’s own codebase (i.e., not bundled reference material), which the agent then uses to generate candidate claims and report/fix actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata