The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from multiple sources, including external LinkedIn post history (via Apify), local project files (about-me.md, voice.md), and user-provided drafts. This creates a surface for indirect prompt injection where malicious instructions embedded in these data sources could influence the agent's scoring or rewriting behavior.
Ingestion points: Data returned from the apimaestro/linkedin-profile-posts Apify actor, local files matching *-all-posts.json, about-me.md, voice.md, and the user's post content.
Boundary markers: Absent. The instructions do not specify the use of delimiters or guidelines to ignore instructions embedded within the ingested text.
Capability inventory: The skill has the ability to read local files, call the Apify tool, and generate rewritten content based on analyzed patterns.
Sanitization: Absent. There is no evidence of filtering or escaping logic applied to the external data before it is analyzed by the agent.
[EXTERNAL_DOWNLOADS]: The skill fetches external data by invoking an Apify actor (apimaestro/linkedin-profile-posts) and downloading the results to the local project environment. While the service is well-known, the skill stores these external datasets as [username]-all-posts.json for subsequent processing.

post-scorer