The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted external data that could contain hidden instructions intended to manipulate the agent.
Ingestion points: The 'Starting Up' workflow (SKILL.md) describes processing a 'project mandate or request' and 'initial business context', while 'Controlling a Stage' processes 'progress updates' and 'impediment reports' from various roles.
Boundary markers: There are no explicit instructions or delimiters defined to isolate external project data or to instruct the agent to ignore instructions embedded within those documents.
Capability inventory: The skill is configured with access to the Bash, Read, Grep, and Glob tools, providing a technical surface for command execution if the agent is successfully manipulated by malicious data.
Sanitization: The skill does not implement or describe any sanitization, filtering, or validation logic for the external inputs it processes.

project-manager