Caveat verdict

lobster-memory

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Accesses agent memory AND writes files

Local memory management skill that writes session notes to local markdown files; file read/write and agent_memory used legitimately for persistence, no network exfiltration.

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

30
security
70
transparency
90
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination high

Accesses agent memory AND writes files — may modify agent behavior persistently

LLM01 · LLM06 · ASI01 · ASI06

Capability combination medium

Both reads and writes files — verify scope is limited to intended directories

LLM06 · ASI02

Permission integrity

Performs file operations but does not declare file-accessing binaries

file_read+write

Accesses agent memory/configuration files

agent_memory

Findings (3)

Confirmed in code medium

File write/delete operation

SKILL.md · code

Pattern match medium

References agent memory files

SKILL.md · code · MEMORY.md

Confirmed in code low

File read operation

SKILL.md · code

Permissions & capabilities

No declared permissions — minimal attack surface.

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