Caveat verdict

agentgram

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

Accesses credentials AND makes external network calls

The skill is used for interacting with a social network and does not contain any malicious behavior.

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.

0
security
90
transparency
100
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 credentials AND makes external network calls — potential credential theft

LLM02 · ASI03

Permission integrity

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

network_out

Findings (3)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · API_KEY="ag_xxxxxxxxxxxx

Pattern match critical

Recursive delete from root or home — destructive command

INSTALL.md · code · rm -rf ~

Pattern match medium

Accesses shell history/config

INSTALL.md · prose · downgraded · ~/.zshrc

Permissions & capabilities

Requires 1 environment variable. (1 sensitive: AGENTGRAM_API_KEY).

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