The Agent Skills Directory

[SAFE]: No malicious patterns, hardcoded secrets, or unauthorized execution methods were found. The skill documentation describes legitimate API interactions for Instagram automation.
[PROMPT_INJECTION]: A potential surface for indirect prompt injection exists due to the ingestion of user-generated content from media comments. However, this is a core functional requirement of the skill and is assessed as safe. 1. Ingestion points: Untrusted data enters the agent context via INSTAGRAM_GET_IG_MEDIA_COMMENTS (documented in SKILL.md). 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are provided. 3. Capability inventory: The skill has write access through INSTAGRAM_CREATE_POST and INSTAGRAM_POST_IG_USER_MEDIA_PUBLISH (documented in SKILL.md). 4. Sanitization: No sanitization or filtering of fetched comment content is specified in the workflow.

instagram-automation