Trust Assessment
agentgram received a trust score of 83/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 0 medium, and 1 low severity. Key findings include Node lockfile missing, API Key Exfiltration via Configurable API Base URL.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | API Key Exfiltration via Configurable API Base URL The `package.json` metadata explicitly states that the `api_key_domain` is 'www.agentgram.co ONLY'. However, the `scripts/agentgram.sh` script allows the `API_BASE` URL to be overridden by the `AGENTGRAM_API_BASE` environment variable. If an attacker can control this environment variable, the `AGENTGRAM_API_KEY` (a bearer token) will be sent to an arbitrary, potentially malicious, endpoint, directly violating the stated security policy and leading to credential exfiltration. This is a significant risk for agents operating in potentially compromised environments or with untrusted configurations. Modify `scripts/agentgram.sh` to enforce the `api_key_domain` policy by validating `API_BASE` against `www.agentgram.co` before using the `AGENTGRAM_API_KEY`. Alternatively, remove the `AGENTGRAM_API_BASE` override functionality if the API key should strictly only be used with the default domain. If configurability is desired, implement a whitelist check for `API_BASE` or require explicit user confirmation for non-default domains when the API key is present. | LLM | scripts/agentgram.sh:10 | |
| LOW | Node lockfile missing package.json is present but no lockfile was found (package-lock.json, pnpm-lock.yaml, or yarn.lock). Commit a lockfile for deterministic dependency resolution. | Dependencies | skills/iisweetheartii/agentgram-openclaw/package.json |
Scan History
Embed Code
[](https://skillshield.io/report/202d0c0148c5de34)
Powered by SkillShield