azure-communication-chat-java
Verdict safe, but 1 finding (1 medium), mainly data exfiltration. Most recent scan 2026-02-05.
This Azure Communication Chat Java SDK skill is primarily a DOCUMENTATION AND REFERENCE skill with MEDIUM security concerns. The skill provides code examples and API usage patterns for Azure Communication Services but does not contain executable scripts or autonomous behaviors. Primary concerns are: (1) Code examples that could encourage credential hardcoding practices (MEDIUM severity), (2) Missing metadata fields that reduce transparency (LOW severity), (3) A missing referenced file that creates package incompleteness (LOW severity), and (4) An incomplete code example that could mislead users (LOW severity). The skill does not exhibit malicious behavior, data exfiltration, prompt injection, or tool exploitation. It functions as intended - providing Java SDK documentation and examples. However, the credential handling patterns in examples could lead to security issues in downstream implementations if users copy-paste without understanding secure practices.
Scanner's overall assessment (LLM analyzer)
Second scanner: NVIDIA SkillSpector
Independent static run, no language model, over the same files as the Cisco scan above. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Build real-time chat applications with Azure Communication Services Chat Java SDK. Use when implementing chat threads, messaging, participants, read receipts, typing notifications, or real-time chat features.
- Package
- 3 files, 27 KB
- SKILL.md
- 779 words, 12+ sections
- Code
- None. Instructions only.
SKILL.md covers: Azure Communication Chat (Java) · Installation · Client Creation · Key Concepts · Create Chat Thread · Send Messages · Get Messages · Update and Delete Messages · Manage Participants · Read Receipts · Typing Notifications · Thread Operations
Findings
MEDIUM Hardcoded Credentials in Code Examples Data Exfiltrationllm
The instruction body contains placeholder patterns for sensitive credentials including user access tokens and user IDs that could lead to accidental credential exposure if users copy-paste examples without proper sanitization. The examples show '<user-access-token>' and '<user-id-1>' patterns which may encourage developers to hardcode credentials directly in source code rather than using secure credential management practices.
SKILL.md
String userAccessToken = "<user-access-token>"; ... new CommunicationUserIdentifier("<user-id-1>")What is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 9.3 KB |
references/acceptance-criteria.md | doc | 6.3 KB |
references/examples.md | doc | 11 KB |
External hosts referenced
contoso.com github.com myresource.communication.azure.com
Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.
Environment variables referenced
AZURE_COMMUNICATION_ENDPOINT AZURE_COMMUNICATION_USER_TOKEN
Package contents recorded 2026-10-22 at commit cfbcbbdc679c. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.
What we checked
- Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
- Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
- Llm analyzer. A language model reads the skill and reports intent-level issues the rules cannot express.
- Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.
- Meta analyzer. A second model pass that validates, deduplicates and re-scores the other analyzers' findings.
What we did not check
- Runtime behaviour. The skill was not executed; findings come from reading its files.
- Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
- Content the analyzers cannot read: images, binaries, and some non-English text.
- Known scanner bypass classes. See the methodology and limitations page.
Sources
- Repository: https://github.com/microsoft/agent-skills
- Raw scan result: github-skills-azure-communication-chat-java-scan.json
- Badge for your README:
- Request a re-scan