The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it instructs the agent to ingest and process untrusted external data, such as support tickets, customer reviews, and interview notes, into structured artifacts.
Ingestion points: Market evidence inputs (interviews, tickets, surveys, reviews) processed in SKILL.md.
Boundary markers: None; the templates do not utilize delimiters or specific instructions to the agent to disregard potential instructions embedded within the ingested data.
Capability inventory: The skill utilizes Bash, Write, Read, and Edit tools to perform its tasks.
Sanitization: There are no sanitization or validation routines defined for the external content before it is processed or written to files.
[COMMAND_EXECUTION]: The skill directs the agent to use the Bash tool for converting Markdown files to .docx format. If the agent incorporates user-provided strings, such as company or contact names, into shell commands without proper escaping, it could lead to command injection vulnerabilities depending on the underlying conversion utility used.

pm-market-problems