saccoai-competitive-analysis
Pass
Audited by Gen Agent Trust Hub on Mar 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches content from external websites provided by the user or discovered via automated search queries to gather benchmarking data.
- [COMMAND_EXECUTION]: Orchestrates the execution of sub-skills and internal tools, specifically
saccoai-website-analysis,agent-browser, andsaccoai-proposal, to perform parallel crawling and report generation. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from external websites which is subsequently processed by the agent to create narrative reports.
- Ingestion points: HTML content, meta tags, and technical signals from external domains (SKILL.md, Phase 1).
- Boundary markers: Absent; the instructions do not specify delimiters or directions to ignore instructions embedded within the crawled content.
- Capability inventory: Performs file writes to the local
.saccoai/directory and triggers thesaccoai-proposalskill to integrate findings into client documents. - Sanitization: Absent; the workflow normalizes and benchmarks data without explicit sanitization or filtering of text retrieved from the target websites.
Audit Metadata