job-finder
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches and installs external components required for its operation.
- Automatically triggers the installation of the
@monid-ai/clipackage from the global NPM registry if the binary is missing. - Instructs the agent to download a remote skill configuration file from
https://monid.ai/SKILL.mdto keep its execution environment updated. - [COMMAND_EXECUTION]: The skill attempts to establish a persistence mechanism through user-assisted automation.
- Explicitly suggests that the user or agent configure a system cron job (
crontab -e) to execute the agent on a daily schedule. - [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection due to its core data processing logic.
- Ingestion points: The skill fetches raw social media content (tweets and LinkedIn posts) from external providers using the
monidCLI. - Boundary markers: There are no specific instructions or delimiters mentioned to isolate external data from the agent's instructions during processing or digest generation.
- Capability inventory: The agent has the capability to execute shell commands (via the
monidCLI) and perform file system operations (writing state and markdown digests). - Sanitization: No sanitization or validation logic is defined to filter malicious instructions embedded in the job postings before they are processed by the agent.
Audit Metadata