daily-briefing-builder
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads and processes the content of Markdown files from a user's local vault. If these files contain malicious instructions, they could potentially influence the agent's behavior. 1. Ingestion points: File reads from vault paths in SKILL.md and SKILL-OC.md (e.g., $VAULT/bambf/tracking/daily-actions/). 2. Boundary markers: None. The skill does not use specific delimiters or instructions to ignore embedded content. 3. Capability inventory: The agent is granted access to bash for shell command execution and curl for network requests. 4. Sanitization: No sanitization or filtering is performed on the content extracted from the vault files.
- [COMMAND_EXECUTION]: The skill instructions direct the agent to interpolate user-provided inputs (vault_path and city) directly into shell script templates. This pattern can lead to command injection if inputs contain shell metacharacters.
- [EXTERNAL_DOWNLOADS]: The skill uses curl to fetch weather data from wttr.in, which is a well-known service for weather information. This is a legitimate functional requirement.
Audit Metadata