limpieza-disco-macos
Warn
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: MEDIUMPRIVILEGE_ESCALATIONCREDENTIALS_UNSAFECOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PRIVILEGE_ESCALATION]: The skill instructs the agent to use
sudofor high-privilege tasks, including erasing system diagnostics and logs (sudo log erase --all) and auditing restricted system directories like/private/var/db/. - [CREDENTIALS_UNSAFE]: The instructions direct the agent to access
auth.jsonto retrieve a deployment token for the Vercel API. This file is a sensitive location used for storing authentication credentials. - [COMMAND_EXECUTION]: The skill executes a wide range of system-level commands to audit the environment, including
launchctlfor service status,lsoffor monitoring network ports, andtmutilfor managing Time Machine snapshots. - [DATA_EXFILTRATION]: Local system metadata, such as OS version, active network services, and detailed file system paths/sizes, is collected and transmitted to external services (Vercel and Discord) as part of the reporting process.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local file system (filenames and directory structures) as input for shell commands.
- Ingestion points: Local file system metadata retrieved via commands like
find,du, andls(SKILL.md). - Boundary markers: None identified; command outputs are directly interpolated into the analysis flow.
- Capability inventory: Subprocess execution with
sudo, sensitive file system access, and network operations (POSTrequests). - Sanitization: The skill recommends the use of
-print0andxargs -0to mitigate risks associated with special characters in filenames.
Audit Metadata