ClawAudit verdict

self-evolving-memory

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

This skill orchestrates local memory routing (SESSION-STATE.md, memory/ directory, MEMORY.md) with no external exfiltration; all operations are file-local and the credential_access capability is incidental to env-var reads typical of any agent framework.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

15
security
30
transparency
70
maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Accesses agent memory/configuration files

agent_memory

Findings (3)

Pattern match critical

Pipe-to-shell pattern (curl | sh) — supply chain attack vector

references/embedding-setup.md · code · curl -fsSL https://ollama.ai/install.sh | sh

Pattern match critical

Pipe to sh — executes piped content as shell commands

references/embedding-setup.md · code · | sh

Pattern match medium

References agent memory files

SKILL.md · code · MEMORY.md

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/B). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

credential_accessagent_memory

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API