competitor-engagers
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using
npm run competitor-engagersfor authentication preflight checks and the main data collection process. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions.
- Ingestion points: The skill fetches comments and reactor data from LinkedIn via the Realtime LinkedIn Bulk Data API and saves them to a CSV file in
~/output/. - Boundary markers: There are no explicit instructions or delimiters mentioned to ensure the agent ignores potentially malicious text embedded within the scraped LinkedIn comments when reading the resulting CSV.
- Capability inventory: The skill utilizes shell command execution (
npm run) and filesystem access (reading/writing to~/output/and~/.env). - Sanitization: No sanitization or filtering logic is described to cleanse the ingested social media content before the agent processes the summary of the engagers.
Audit Metadata