trial-reels
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Executes several Python scripts located within the plugin's internal library and skill directories (
review.py,retakes.py,edit.py,post.py) to process video files and manage social media posting. This is a core part of the skill's functionality. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from video transcripts and external links to plan and generate content variations. This surface could be exploited if malicious instructions are embedded in the source video metadata or transcripts.
- Ingestion points: Reads transcripts from
words.raw.jsonand accepts external Reel links or posted files from the user. - Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions embedded within the processed video data.
- Capability inventory: The skill has the ability to post content to social media (
post.py), modify local files and directories (edit.py), and communicate with the user via a review interface (review.py). - Sanitization: There is no mention of sanitizing or validating the content of transcripts before the AI uses them to 'Name the type' or 'Plan' variations.
Audit Metadata