skills/cybercentry/cybercentry-agent-skills/cybercentry-quantum-cryptography-verification/Gen Agent Trust Hub
cybercentry-quantum-cryptography-verification
Warn
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: MEDIUMDATA_EXFILTRATIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill provides bash scripts that read contents from sensitive local files, such as .env and sensitive_data.txt, and transmit them to the Cybercentry service via network requests.
- [COMMAND_EXECUTION]: The skill contains multiple scripts that execute shell commands to read files, write to local storage (~/.secure/encrypted_credentials.csv), and interact with external CLI tools.
- [EXTERNAL_DOWNLOADS]: The instructions guide users to download and install the ACP platform from a third-party GitHub repository (Virtual-Protocol/openclaw-acp).
- [PROMPT_INJECTION]: As the skill processes arbitrary text data from users or files and interacts with network services and local file systems, it presents an attack surface for indirect prompt injection if the processed data contains malicious instructions. (Ingestion points: local file reading and user input in SKILL.md; Boundary markers: Absent; Capability inventory: acp job create for network transmission and file read/write operations in bash scripts; Sanitization: Absent, relies on manual user review.)
Audit Metadata