agent-id-vault
agent-id-vault is an API access & connector plumbing skill for AI agents, published by alien-id in the agent-id repository on GitHub. Skillspace rates agent-id-vault F (45/100) and the safety scan rated it risky; the rating is based on static analysis only.
Risky. This skill has patterns associated with unsafe behaviour. Read the source carefully before running it.
Portable encrypted credential vault with LUKS-style slots (passkey/Touch ID, passphrase, agent-key, phone) and typed/domain-scoped credential records. Credentials can carry an ACCESS LEVEL (--access ro) so the agent can read a service but never write to it — enforced by the proxy and the sealed browser, widened only with the owner's out-of-band confirmation (set-access). Pairs with agent-id-proxy so the agent never sees credential values — the proxy injects them at request time. Can also GENERATE blockchain wallet keys (Solana ed25519, EVM secp256k1) inside the vault — the private key is sealed, only the address is printed, and transactions are signed by the proxy. Use whenever the user asks to save, fetch, or remove a service credential, create a crypto wallet for the agent, or whenever a downstream tool needs an external-service secret that must not appear in shell history, source files, or process arguments.
- Grade
- F
- Quality
- 45 / 100
- Safety
- Risky
- GitHub stars
- 32
Unproven: rated by static analysis only, not yet compared head-to-head.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since.
Our review
- Architecture
- 99 / 100
- Maturity
- Packaged: licensed, with a version or references
- Security scan
- High-risk patterns
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- accesses sensitive system files
- reads environment variables
- over-broad allowed-tools ('*')
- mentions secrets in text
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- 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.