The Agent Skills Directory

[SAFE]: The skill operates entirely within the local workspace, processing text data to generate content strategies. No malicious code, obfuscation, or data exfiltration patterns were found in the instructions or reference materials.- [PROMPT_INJECTION]: The skill ingests raw ideas from users and outputs from other tools like the trend-researcher. While this represents a potential surface for indirect prompt injection, the skill's capabilities are strictly limited to reading and writing local text files, which prevents exploitation of dangerous system functions.
Ingestion points: Raw idea input and trend-researcher output referenced in SKILL.md.
Boundary markers: The skill does not use specific delimiters to isolate external data.
Capability inventory: Restricted to Read and Write tools for local workspace management.
Sanitization: No explicit content filtering or validation is performed on ingested data before it is processed.

episode-strategist