earnings-revenue-guidance
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted corporate earnings call transcripts which are ingested into the agent context.
- Ingestion points: Transcripts are accessed during revenue extraction steps in
SKILL.md. - Boundary markers: No specific delimiters or instructions to ignore embedded content are provided in the prompts.
- Capability inventory: The agent uses the
octagon-mcptool for data processing and analysis. - Sanitization: No sanitization of the transcript content is performed.
- [EXTERNAL_DOWNLOADS]: The skill facilitates the download of the
octagon-mcppackage from the npm registry and the Homebrew installation script from GitHub. - [REMOTE_CODE_EXECUTION]: The setup instructions involve executing the
octagon-mcptool vianpxand running the Homebrew installer through a shell script. These represent standard installation procedures for the vendor's own infrastructure and well-known developer services.
Audit Metadata