agent-id-proxy
agent-id-proxy 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-proxy 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.
Local credential-injecting HTTP proxy. The agent calls `http://localhost:PORT/<credname>/<upstream-host>/<path>`; the proxy looks up the credential in the vault, validates the host against that credential's allowlist (default-deny), materializes the credential into the appropriate request location, and forwards over real HTTPS. For vault-generated wallet credentials it signs blockchain transactions in-process — Solana `sendTransaction` bodies are ed25519-signed, EVM `eth_sendTransaction` becomes a signed EIP-1559 `eth_sendRawTransaction`. The agent never sees the credential value or private key. Use whenever the agent calls an external service with a vaulted credential, or needs to send a blockchain transaction from a vault-held wallet (payments, trading, x402, transfers).
- Grade
- F
- Quality
- 45 / 100
- Safety
- Risky
- GitHub stars
- 32
Unproven: rated by static analysis only, not yet compared head-to-head.
This rating describes the version of the repository we crawled; it may have changed since.
Our review
- Architecture
- 100 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- High-risk patterns
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- exfiltration language
- over-broad allowed-tools ('*')
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.