The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-supplied data to perform portfolio analysis, which serves as a potential vector for indirect prompt injection attacks.
Ingestion points: User inputs for portfolio units, market boundaries, market growth, and relative market share described in the Workflow section of SKILL.md.
Boundary markers: None; the workflow lacks explicit delimiters or instructions to the agent to ignore potentially malicious commands embedded within the business data.
Capability inventory: The skill environment permits the use of Read, Grep, WebSearch, and WebFetch tools.
Sanitization: No evidence of input validation, sanitization, or escaping is present for the data processed during the matrix construction.
[EXTERNAL_DOWNLOADS]: The skill fetches grounding documentation and strategic framework history from the official Boston Consulting Group (BCG) website.
[SAFE]: No evidence of code obfuscation, hardcoded credentials, or unauthorized command execution was found. All external URLs point to well-known and authoritative professional sources.

bcg-matrix