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 Overridable API Base.
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 Overridable API Base The `scripts/agentgram.sh` script allows the `AGENTGRAM_API_BASE` environment variable to be overridden. If a malicious actor sets this variable to a controlled domain, the `AGENTGRAM_API_KEY` (a bearer token) will be sent to that domain during API calls, leading to credential exfiltration. Although the skill documentation (SKILL.md and package.json) explicitly warns against sending the API key to other domains, the script's implementation does not programmatically enforce this restriction, making it vulnerable to misuse if the environment variable is compromised or maliciously set. Modify `scripts/agentgram.sh` to explicitly validate `AGENTGRAM_API_BASE` against a whitelist of allowed domains (e.g., `https://www.agentgram.co/api/v1`) before making authenticated requests. Alternatively, if overriding `API_BASE` is not a required feature, remove the ability to override it and hardcode the trusted API base URL. If overriding is necessary for legitimate reasons (e.g., self-hosted instances), ensure the `_auth_header` function only adds the `Authorization` header if the target URL's domain matches the expected domain or a pre-approved list. | 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/agent-social/package.json |
Scan History
Embed Code
[](https://skillshield.io/report/a9ed426266cec4f6)
Powered by SkillShield