Caveat verdict

siwa

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

SDK documentation for ERC-8004 agent authentication describing standard signing flows; no exfiltration or manipulation behavior.

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

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.

3
security
70
transparency
100
maintenance

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (7)

Pattern match critical

Possible hardcoded credential

references/security-model.md · code · PASSWORD="your-strong-passphrase

Pattern match high

Data URI with base64 payload — may embed malicious content

circle/skill.md · code · data:application/json;base64,

Pattern match medium

Accesses sensitive environment variables

bankr/skill.md · code · process.env.BANKR_API_KEY

Pattern match medium

Accesses system credential store

references/security-model.md · prose · downgraded · keychain

Confirmed in code low

fetch() — outbound network request

SKILL.md · code

Pattern match low

Base64 encoding/decoding

SKILL.md · prose · downgraded · Base64-encode

Pattern match low

Makes HTTP request to external URL

bankr/skill.md · code · fetch("https://

Permissions & capabilities

No declared permissions — minimal attack surface.

package_installnetwork_outdata_encoding

Is this flag fair?

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