asterisk-validator
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
docker execcommand to interact with the MikoPBX container, allowing the agent to run arbitrary shell commands and Asterisk CLI operations (asterisk -rx). This constitutes high-privilege command execution within the managed environment. - [DATA_EXFILTRATION]: The skill accesses and reads content from sensitive configuration files, including
/etc/asterisk/pjsip.confand/etc/asterisk/extensions.conf, as well as the SQLite database at/cf/conf/mikopbx.db. These files contain SIP authentication credentials (usernames and passwords) and dialplan logic. While the skill's stated purpose is validation, accessing these paths exposes sensitive information to the agent context. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from log files and configuration files, creating a potential surface for indirect prompt injection. 1. Ingestion points: Reads Asterisk configuration files and logs from
/storage/usbdisk1/mikopbx/log/and/etc/asterisk/. 2. Boundary markers: The instructions do not specify any delimiters or safety markers to isolate external content when it is read into the context. 3. Capability inventory: The skill has the ability to execute commands viaBashanddocker execand perform file-read operations. 4. Sanitization: There is no mention of sanitizing or filtering the content of the logs or configuration files before they are analyzed.
Audit Metadata