manage-mounts
manage-mounts is an Agent security & guardrails skill for AI agents, published by nanocoai in the nanoclaw repository on GitHub. Skillspace rates manage-mounts D (68/100) and it passed the safety scan; a judge model has also reviewed it.
Configure which host directories agent containers can access. View, add, or remove mount allowlist entries. Triggers on "mounts", "mount allowlist", "agent access to directories", "container mounts".
- Grade
- D
- Quality
- 68 / 100
- Safety
- Passed
- GitHub stars
- 30,754
Placed #5 of 6 in the judged category final for Agent security & guardrails.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 100 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
Judge review
Placed #5 of 6 in the judged category final for Agent security & guardrails.
- Trigger
80 80 - Instructions
82 82 - Specificity
78 78 - Safety
88 88 - Disclosure
60 60 - Maintenance
65 65
Straightforward sandbox-allowlist editor that defaults to read-only and validates paths before writing, though the whole skill is only a few commands deep.
Not checked yet
- Category is a classifier prediction; no model has read this skill yet
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.