The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute local Python scripts located within the plugin's infrastructure. Specifically, it runs campaign-tracker.py to list and manage marketing campaigns and benchmark_book.py to record or quote industry pricing benchmarks. These operations are restricted to internal plugin scripts and are consistent with the skill's stated purpose.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources, creating a potential surface for indirect prompt injection. It reads brand profiles, industry profiles, and brand guidelines from the local filesystem (~/.claude-marketing/), and it processes user-supplied descriptions of brand crises or customer reviews. While these sources could theoretically contain adversarial instructions, this is a standard risk for skills that aggregate and process external information.
Ingestion points: Brand profiles (profile.json), brand guidelines (_manifest.json), industry profiles, and user-provided descriptions of reputation incidents.
Boundary markers: The skill does not explicitly define delimiters or boundary markers to isolate ingested content from its primary instructions.
Capability inventory: The agent has the capability to execute local scripts and perform filesystem reads to retrieve configuration data.
Sanitization: There is no evidence of explicit sanitization or validation of the content read from the brand profile files or user inputs before processing.

reputation-management