halo-cli-moderation-notifications
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it involves reading and acting upon external, user-supplied data.
- Ingestion points: The agent fetches potentially untrusted data via 'halo comment list' and 'halo notification list' as described in SKILL.md.
- Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions within the processed content.
- Capability inventory: The skill empowers the agent to perform sensitive actions like 'approve', 'delete', and 'create-reply' based on the ingested data in SKILL.md.
- Sanitization: No sanitization or validation of the external content is performed before the agent processes or responds to it.
Audit Metadata