The Agent Skills Directory

[COMMAND_EXECUTION]: The skill constructs and executes shell commands using the local script audience-simulator.py by interpolating user-provided inputs such as {id} and {slug}. This pattern is susceptible to command injection if the input strings are not properly sanitized or validated before being passed to the shell environment.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by ingesting untrusted data from multiple local sources to guide agent behavior.
Ingestion points: Reads brand profiles, guidelines, and CRM data from ~/.claude-marketing/brands/{slug}/profile.json and ~/.claude-marketing/brands/{slug}/guidelines/_manifest.json (SKILL.md).
Boundary markers: The instructions do not specify any delimiters or explicit warnings to the agent to ignore or isolate embedded instructions within these ingested data sources.
Capability inventory: The skill has the capability to execute shell commands and read files across the local system (SKILL.md).
Sanitization: There is no evidence of content sanitization, escaping, or schema validation for the data retrieved from external files before it is processed by the language model.

pricing-test